© 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. 11-RESID-POST-AA
    11. 24558
    Prev
    Next
    INDEX
    Explanations

    HTML code

    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
     thorough
    -0.08
    行
    -0.08
    巧
    -0.07
    Tour
    -0.07
    完善
    -0.07
    ;m
    -0.07
     megs
    -0.07
    成本
    -0.07
    試
    -0.07
    起
    -0.07
    POSITIVE LOGITS
     состояние
    0.09
     Status
    0.09
     Placeholder
    0.09
     Anzeige
    0.09
     состояния
    0.09
     главный
    0.09
     Vict
    0.08
     Dynam
    0.08
     utama
    0.08
     witnessing
    0.08
    Activations Density 0.017%

    No Known Activations