© 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. 71151
    Prev
    Next
    INDEX
    Explanations

    ne

    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
     nostru
    -0.10
     السياسي
    -0.09
    Opcode
    -0.09
     asfalt
    -0.09
     deployments
    -0.09
     المسلم
    -0.08
     Opcode
    -0.08
     bruto
    -0.08
     opcode
    -0.08
     asphalt
    -0.08
    POSITIVE LOGITS
     herself
    0.17
     née
    0.15
     feminist
    0.15
     women
    0.15
     woman
    0.15
     motherhood
    0.14
     feminism
    0.14
     женщина
    0.14
     feminina
    0.14
     Women
    0.13
    Activations Density 1.399%

    No Known Activations