© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65499
    Prev
    Next
    INDEX
    Explanations

    projectiles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gymnastics
    -0.08
     presenting
    -0.08
    -building
    -0.07
     rewriting
    -0.07
    (Configuration
    -0.07
    emás
    -0.07
    washing
    -0.07
     somm
    -0.07
    alty
    -0.07
     summed
    -0.07
    POSITIVE LOGITS
     missiles
    0.12
     projectile
    0.12
     travels
    0.11
     fired
    0.11
     missile
    0.10
    Tracer
    0.10
    Projectile
    0.10
    穿
    0.10
     traveled
    0.10
    送
    0.10
    Activations Density 0.024%

    No Known Activations