Christopher Olah is a Canadian machine learning researcher and co-founder of [[Anthropic]], specializing in neural network interpretability — the effort to understand what AI systems are actually doing internally. His pioneering work on visualizing and understanding deep learning models has been foundational to the field of mechanistic interpretability. Olah's research agenda represents the technical wing of the [[AI Safety]] movement, distinct from but connected to the policy and governance approaches within the broader [[Effective Altruism]] community.