© 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. 23-RESID-POST-AA
    11. 96863
    Prev
    Next
    INDEX
    Explanations

    **

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ехнолог
    -0.08
     المكت
    -0.07
     кабинет
    -0.07
     baccarat
    -0.07
    dim
    -0.07
    <Book
    -0.07
    etzung
    -0.07
    ρ
    -0.07
    歲
    -0.07
    _modules
    -0.07
    POSITIVE LOGITS
     apparel
    0.24
     Apparel
    0.20
     clothing
    0.20
     ടി
    0.20
     tees
    0.18
     shirts
    0.18
     camiseta
    0.18
     t
    0.18
     vêtements
    0.17
     tee
    0.17
    Activations Density 0.026%

    No Known Activations