corpus.blog
42,697 blogs · 5,350,595 posts Claim your blog
Record · corpus.blog/posts/01a08c64-363c-71f8-9e1a-887678940914

Natural Language Autoencoders: Turning Claude’s thoughts into text

Anthropic · published 6 May 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at anthropic.com Wayback capture
3blogs citing
First cited
19 May 2026
Most recent
24 May 2026
Rank this month
not ranked
External links
12
Words captured
1,857

Cited by

Blog
In the post
Date
turntrout.com
Eval Cooperativeness May Be a Scalable Mitigation for Eval Gaming Read at the source ↗
24 May 2026
subatomicarticles.com
Claude Mythos and the tower of holes Read at the source ↗
20 May 2026
The Garden 🌿
Mx Tynehorne’s link roundup, volume LXV Read at the source ↗
19 May 2026

Links from this post

Link
Host
https://transformer-circuits.pub/2023/monosemantic-features
transformer-circuits.pub
https://transformer-circuits.pub/2024/scaling-monosemanticity/
transformer-circuits.pub
On the Biology of a Large Language Model Read at the source ↗
transformer-circuits.pub
Circuit Tracing: Revealing Computational Graphs in Language Models Read at the source ↗
transformer-circuits.pub
http://neuronpedia.org/nla
neuronpedia.org
https://github.com/kitft/natural_language_autoencoders
github.com
http://claude.ai/redirect/website.v1.c239b2c0-2d66-40d7-8801-d05448c97385
claude.ai
http://claude.ai
claude.ai
https://arxiv.org/abs/2412.08686
arxiv.org
https://arxiv.org/abs/2510.05092
arxiv.org
https://transluce.org/pcd
transluce.org
Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations Read at the source ↗
transformer-circuits.pub
Elsewhere on anthropic.com (13)
https://www.anthropic.com/research/agentic-misalignment
anthropic.com
https://www-cdn.anthropic.com/963373e433e489a87a10c823c52a0a013e9172dd.pdf
www-cdn.anthropic.com
https://assets.anthropic.com/m/64823ba7485345a7/Claude-Opus-4-5-System-Card.pdf
assets.anthropic.com
https://www-cdn.anthropic.com/0dd865075ad3132672ee0ab40b05a53f14cf5288.pdf
www-cdn.anthropic.com
https://www-cdn.anthropic.com/53566bf5440a10affd749724787c8913a2ae0841.pdf
www-cdn.anthropic.com
Automated Auditing Read at the source ↗
alignment.anthropic.com
https://www-cdn.anthropic.com/08ab9158070959f88f296514c21b7facce6f52bc.pdf
www-cdn.anthropic.com
https://www-cdn.anthropic.com/14e4fb01875d2a69f646fa5e574dea2b1c0ff7b5.pdf
www-cdn.anthropic.com
https://alignment.anthropic.com/2026/introspection-adapters/
alignment.anthropic.com
Circuits Cross-Post — Activation Oracles Read at the source ↗
alignment.anthropic.com
https://www.anthropic.com/research/project-swap
anthropic.com
https://www.anthropic.com/research/claude-uplifts-biomolecular-modeling
anthropic.com
https://www.anthropic.com/research/intelligence-targeting-conventional-weapons-capabilities
anthropic.com