Chris Olah

One of the earlier Anthropic contributors worth tracking if you care about the transition from RLHF-style assistant training into scaling and evaluation work.

One of the clearest people to follow if you want the mechanistic-interpretability thread at Anthropic rather than only its safety-policy surface.

Useful for the seam between Anthropic’s earlier alignment papers and its later audit-oriented safety work, where interpretability and evaluation start feeding into deployment practice.

One of the most important people to follow for mechanistic interpretability and transformer-circuits-style attempts to reverse engineer how large language models work.

A high-signal figure for understanding the frontier model era because his work sits at the intersection of scaling, post-training, and deployment-risk framing.

A high-signal researcher for understanding how post-training and behavioral steering become concrete product behavior rather than abstract alignment talk.