STEERING ARENA

STEER THE MODEL'S MIND — ▲ PRO‑HUMAN OR ▼ ANTI‑HUMAN. ONE SCORE, TWO BOARDS.

HOW TO PLAY

NEW CHALLENGER

A short string that, prepended to neutral prompts, shifts the model's last-token state along the direction — ▲ toward pro-human or ▼ against it. One submission scores once and ranks on both boards. Weird, opaque sequences are fair game.

Your handle and sequence are public on the leaderboard. Don't enter personal or sensitive information.

/ TOK over budget
▲ RANK PRO · ▼ RANK ANTI · SPEC · TOK
GAME OVER

HIGH SCORES

Scores are shifts along a learned activation direction — not measurements of moral content or behavioral safety. Limitations →

#PLAYERSEQUENCESCORESPEC

NO SCORES YET
BE THE FIRST

CONTACT THE OPERATOR

Steering Arena is a non-commercial research project by Soham Padia — ML Engineer & Researcher, MS in Artificial Intelligence at Northeastern University (Boston, MA). Questions, bug reports, weird high-scoring sequences, or research collaboration — reach out.

✉ EMAIL ▣ WEBSITE ⌥ GITHUB in LINKEDIN ✕ TWITTER ✦ SCHOLAR

CITE THIS

Using Steering Arena in research, a write-up, or a class? Please cite it:

BibTeX

@misc{padia2026steeringarena,
  author       = {Padia, Soham},
  title        = {Steering Arena: A Public Pro-Human Activation-Steering Competition},
  year         = {2026},
  howpublished = {\url{https://sohampadianeu-steering-arena.hf.space}},
  note         = {Non-commercial interpretability research, Northeastern University}
}

Plain text

Padia, S. (2026). Steering Arena: A Public Pro-Human Activation-Steering Competition. https://sohampadianeu-steering-arena.hf.space

Code, seed pairs, directions, and analysis: github.com/soham-padia/steering-arena. Scores are season-specific — note the season (model, layer, direction) shown in the banner above when citing a result.