© 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. 108696
    Prev
    Next
    INDEX
    Explanations

    Dragging and dropping files

    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
    Least
    -0.08
     Least
    -0.08
    least
    -0.08
    precedented
    -0.08
    empor
    -0.08
     livest
    -0.07
     prevalent
    -0.07
     katanya
    -0.07
     least
    -0.07
    ランド
    -0.07
    POSITIVE LOGITS
    ınıza
    0.08
    Folders
    0.08
     feld
    0.07
     bulk
    0.07
     Filed
    0.07
     Bulk
    0.07
     દાખ
    0.07
    เข
    0.07
     కమ
    0.07
    چه
    0.07
    Activations Density 0.002%

    No Known Activations