© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 44467
    Prev
    Next
    INDEX
    Explanations

    Fractions and division of items

    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
    asz
    -0.08
     elected
    -0.08
     nominees
    -0.08
     scam
    -0.08
     schlicht
    -0.07
     lane
    -0.07
     siy
    -0.07
    _dataframe
    -0.07
    -La
    -0.07
     выбирать
    -0.07
    POSITIVE LOGITS
     measurement
    0.08
     slightest
    0.08
     gradual
    0.08
    .Illegal
    0.08
     perfume
    0.08
    037
    0.08
     Indicates
    0.07
    measurement
    0.07
    027
    0.07
    .variable
    0.07
    Activations Density 0.021%

    No Known Activations