© 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. 70049
    Prev
    Next
    INDEX
    Explanations

    Item Set

    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
    اله
    -0.09
    ක්ෂ
    -0.08
    /R
    -0.08
    خول
    -0.08
    ığın
    -0.08
    -अलग
    -0.08
    ellery
    -0.08
    Histogram
    -0.08
    👇
    -0.07
    volen
    -0.07
    POSITIVE LOGITS
     மாந
    0.08
    dert
    0.08
    _uni
    0.07
     Betreiber
    0.07
     unloaded
    0.07
     Lug
    0.07
     analog
    0.07
     Gibt
    0.07
    _deleted
    0.07
    уц
    0.07
    Activations Density 0.002%

    No Known Activations