© 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. 47411
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     convenient
    -0.08
     Bayan
    -0.07
    诉
    -0.07
    ിങ്ങ
    -0.07
    ceil
    -0.07
    вы
    -0.07
    ć
    -0.07
     Raymond
    -0.07
     comod
    -0.07
     financieras
    -0.07
    POSITIVE LOGITS
    最新版
    0.10
     GPT
    0.08
     tokenizer
    0.08
     Improved
    0.08
     GT
    0.08
     Refin
    0.08
     Improving
    0.08
    新版
    0.08
     NLP
    0.08
    draft
    0.08
    Activations Density 0.077%

    No Known Activations