AI Researcher

Neel Nanda Portfolio

Mechanistic interpretability researcher who ran DeepMind's mech interp team and now leads the interpretability track at MATS; his site archives 50+ numbered technical posts reverse-engineering transformer internals, alongside open recruiting and mentorship for new interpretability researchers.

Mechanistic InterpretabilityTransformersAI SafetyDeepMind

What makes it work

A breakdown of the choices that make this portfolio stand out.

1

A numbered post series that functions as a running research log

Sequentially numbered posts (past 50) read like a lab notebook made public — readers can trace how his understanding of transformer circuits evolved rather than seeing only polished conclusions.

2

Mentorship infrastructure built into the site itself

Recruiting and supervising MATS applicants directly from the homepage turns a personal blog into a functioning pipeline for training new interpretability researchers, not just a publishing outlet.

3

Research strategy writing alongside technical writing

"Good Research Takes are Not Sufficient for Good Strategic Takes" addresses how to choose problems, not just how to solve them — a rarer and higher-leverage kind of writing for a field this young.

What AI Researchers can take from this

Specific, actionable tips to apply to your own portfolio — no generic advice.

  • Number your posts and let them read as a running log, not a disconnected greatest-hits feed.

  • If your field is young, build a visible path (a program, a set of starter problems) for newcomers directly into your site.

  • Write occasionally about how you pick research problems, not only about your solutions — it signals judgment, not just execution.

Ready to build your portfolio?

Follow the AI Researcher roadmap — skills, projects, and timeline to get hired.

AI Researcher Roadmap