© 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. 23-RESID-POST-AA
    11. 50989
    Prev
    Next
    INDEX
    Explanations

    Math and numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ekh
    -0.08
     чыккан
    -0.08
     CIS
    -0.08
    ਖ
    -0.08
    렌
    -0.08
     Бишк
    -0.07
     abiding
    -0.07
     kerst
    -0.07
    outlined
    -0.07
    uelto
    -0.07
    POSITIVE LOGITS
     TA
    0.08
     BP
    0.08
     SA
    0.08
    SPA
    0.08
     AA
    0.08
     RA
    0.08
     PA
    0.08
     Chances
    0.08
     secundarios
    0.08
    (bp
    0.08
    Activations Density 0.074%

    No Known Activations