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. 53869
    Prev
    Next
    INDEX
    Explanations

    ured

    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
    -0.08
    Unload
    -0.08
     maupun
    -0.08
    refu
    -0.07
    CSC
    -0.07
     Bland
    -0.07
     Exit
    -0.07
    .xml
    -0.07
    Backward
    -0.07
    303
    -0.07
    POSITIVE LOGITS
    摄影
    0.10
     تصویر
    0.10
     fotografía
    0.10
     photograph
    0.10
     кад
    0.10
     photographed
    0.10
     fotografia
    0.09
     camera
    0.09
     shot
    0.09
    撮
    0.09
    Activations Density 0.001%

    No Known Activations