© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 26145
    Prev
    Next
    INDEX
    Explanations

    ing

    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
    erste
    -0.08
    -0.07
    dalan
    -0.07
    alada
    -0.07
    Highlights
    -0.07
    Ç
    -0.07
    raeg
    -0.07
    发动
    -0.07
    ouz
    -0.07
    ither
    -0.07
    POSITIVE LOGITS
     зан
    0.11
    ирование
    0.09
    ируем
    0.08
    fra
    0.08
    ierung
    0.07
    一下
    0.07
    .Errors
    0.07
    _bool
    0.07
     relationships
    0.07
     validation
    0.07
    Activations Density 0.009%

    No Known Activations