© 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. 129562
    Prev
    Next
    INDEX
    Explanations

    math formulas

    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
     arbor
    -0.09
     fading
    -0.08
     faster
    -0.08
     bonus
    -0.08
     luminos
    -0.08
    キャン
    -0.08
    發布
    -0.08
     glitter
    -0.07
     गिर
    -0.07
     dax
    -0.07
    POSITIVE LOGITS
     новый
    0.09
     Управ
    0.09
     новым
    0.09
     некотор
    0.08
     воду
    0.08
     новое
    0.08
     После
    0.08
     достаточно
    0.08
     круг
    0.08
     первый
    0.08
    Activations Density 0.013%

    No Known Activations