© 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. 78113
    Prev
    Next
    INDEX
    Explanations

    Computer science

    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
     subset
    -0.08
    ILT
    -0.08
     Housewives
    -0.08
    \Bundle
    -0.08
    -range
    -0.08
    _subset
    -0.08
    ocar
    -0.08
    -bind
    -0.08
     abase
    -0.08
    สมาชิก
    -0.08
    POSITIVE LOGITS
    人生
    0.09
    ייר
    0.08
    illon
    0.08
     ഭ
    0.07
    FIELD
    0.07
     Jeśli
    0.07
     Jaw
    0.07
     ölüm
    0.07
    ریل
    0.07
    erno
    0.07
    Activations Density 0.000%

    No Known Activations