© 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. 63292
    Prev
    Next
    INDEX
    Explanations

    negation and foreign languages

    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
    .Expr
    -0.08
    activ
    -0.08
     Activ
    -0.08
    Исп
    -0.08
     enormously
    -0.07
     activ
    -0.07
    edef
    -0.07
     поп
    -0.07
    (math
    -0.07
     ativ
    -0.07
    POSITIVE LOGITS
    ష్ట
    0.08
     thereof
    0.08
     kato
    0.07
    毛
    0.07
    shan
    0.07
     barb
    0.07
     હતા
    0.07
     strani
    0.07
     thread
    0.07
     sier
    0.07
    Activations Density 0.028%

    No Known Activations