Who's Who of AI

Chris Olah

Interpretability researcher at Anthropic

422 trust researcher @colah.bsky.social · 6,868 followers @ch402 · 0 followers
AI research Models & releases Safety & security
Why follow

Interpretability researcher at Anthropic with public evidence across AI research, Models & releases, Safety & security.

AI signals
0
past 30d
Sources
0
distinct domains
Discussions
0
past 30d
Latest signal
—
View every signal from Chris Olah →
Reverse engineering neural networks at Anthropic. Previously Distill, OpenAI, Google Brain.Personal account.
No recent on-topic activity harvested.
Their network

In Chris Olah's orbit

Center = Chris Olah. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.