Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42010
    Prev
    Next
    INDEX
    Explanations

    Run configurations

    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
    _sy
    -0.08
    Aantal
    -0.08
    Assess
    -0.08
    Descripcion
    -0.08
     firms
    -0.08
     potpuno
    -0.08
     FBI
    -0.07
     Fé
    -0.07
    Sy
    -0.07
    淫
    -0.07
    POSITIVE LOGITS
     кноп
    0.09
     кнопку
    0.08
     squeeze
    0.08
     запуск
    0.08
     Potion
    0.08
     Dropdown
    0.07
    0.07
    кон
    0.07
    _INLINE
    0.07
     ў
    0.07
    Activations Density 0.001%

    No Known Activations