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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1280
    Prev
    Next
    INDEX
    Explanations

    coefficient

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abduct
    -0.09
     abandonment
    -0.08
     salvage
    -0.08
    ocr
    -0.08
     CIA
    -0.08
    ক্ষম
    -0.08
     adequ
    -0.08
     takt
    -0.08
    manship
    -0.08
    -0.08
    POSITIVE LOGITS
     flo
    0.08
     Ile
    0.08
    ighbours
    0.08
     quien
    0.08
    러스
    0.07
     '\'
    0.07
    空气
    0.07
    网上
    0.07
     airfare
    0.07
    _HELP
    0.07
    Activations Density 0.014%
    No Known Activations