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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110975
    Prev
    Next
    INDEX
    Explanations

    interest

    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
    Bg
    -0.08
     physi
    -0.08
    Wheel
    -0.08
    Shop
    -0.08
    Del
    -0.07
    _bg
    -0.07
    Distinct
    -0.07
    兴趣
    -0.07
    مين
    -0.07
    ಕ್ಷ
    -0.07
    POSITIVE LOGITS
     Contracts
    0.09
     contrats
    0.08
     paramount
    0.08
     contracting
    0.08
     FLAG
    0.08
     экспер
    0.08
     occident
    0.08
     قرارداد
    0.08
     unor
    0.08
     kontr
    0.08
    Activations Density 0.005%

    No Known Activations