© 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 EvalsExportsAPI 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. 69693
    Prev
    Next
    INDEX
    Explanations

    - or p

    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
     skl
    -0.07
     modus
    -0.07
    modus
    -0.07
     यही
    -0.07
    zust
    -0.07
     anus
    -0.07
     μή
    -0.07
     HIV
    -0.07
     dve
    -0.07
     dva
    -0.07
    POSITIVE LOGITS
     käy
    0.08
    学校
    0.08
    ,password
    0.08
     компания
    0.08
    0.08
     contraseña
    0.08
    컬
    0.08
    аж
    0.08
    ARGS
    0.08
     Verkäufer
    0.07
    Activations Density 0.002%
    No Known Activations