Chris Olah

Chris Olah is a co-founder of Anthropic, where he leads mechanistic-interpretability research aimed at reverse-engineering the internal computations of large neural networks. He previously led interpretability research at OpenAI, worked at Google Brain, and co-founded Distill, a peer-reviewed scientific journal dedicated to clear ML communication. His team's work on dictionary learning and "features" in Claude has identified millions of human-interpretable patterns inside the model. He was named to TIME's 100 Most Influential People in AI in 2024 and is central to Anthropic's goal of opening the AI black box by 2027.