© 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. 70191
    Prev
    Next
    INDEX
    Explanations

    sn

    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
    ברות
    -0.08
     rapidamente
    -0.08
     sâu
    -0.08
     lettere
    -0.08
    Sexo
    -0.08
    Su
    -0.08
     rapidement
    -0.08
    _CTL
    -0.08
    jár
    -0.08
     snabbt
    -0.08
    POSITIVE LOGITS
     गुर
    0.07
     لازم
    0.07
     ढ
    0.07
     moet
    0.07
     응
    0.07
     يجب
    0.07
     blocked
    0.07
     பொ
    0.07
     投
    0.07
    иг
    0.07
    Activations Density 0.000%

    No Known Activations