© 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. 65004
    Prev
    Next
    INDEX
    Explanations

    ^

    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
     virtue
    -0.08
     boil
    -0.08
     Myth
    -0.08
     aerobic
    -0.08
     piercing
    -0.07
    tries
    -0.07
     Augsburg
    -0.07
     shedding
    -0.07
     WHY
    -0.07
    왜
    -0.07
    POSITIVE LOGITS
     后
    0.08
    注明
    0.07
    prs
    0.07
    iation
    0.07
    .SIZE
    0.07
     SER
    0.07
    uchi
    0.07
     /^\
    0.07
    èvement
    0.07
     на
    0.07
    Activations Density 0.012%

    No Known Activations