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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58690
    Prev
    Next
    INDEX
    Explanations

    move

    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
     Packaging
    -0.08
     প্রত্য
    -0.08
     entscheiden
    -0.08
     Erwartungen
    -0.08
     blok
    -0.08
     équilibr
    -0.08
     produits
    -0.08
     Screening
    -0.07
    (Expected
    -0.07
     अपे
    -0.07
    POSITIVE LOGITS
    Mouse
    0.11
    mousemove
    0.10
    (Mouse
    0.10
    Dragged
    0.10
    _mouse
    0.09
    途中
    0.09
    鼠
    0.09
     Mouse
    0.09
    (mouse
    0.09
    _drag
    0.09
    Activations Density 0.002%

    No Known Activations