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. 112888
    Prev
    Next
    INDEX
    Explanations

    Math equations

    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
     Paige
    -0.08
     EO
    -0.08
     Lore
    -0.08
     Bailey
    -0.08
    نگ
    -0.07
    jük
    -0.07
     puff
    -0.07
    لە
    -0.07
     copper
    -0.07
     pygame
    -0.07
    POSITIVE LOGITS
     doctoral
    0.08
    (||
    0.08
    006
    0.08
     &)
    0.08
    0.08
    -guide
    0.07
    025
    0.07
    ancellation
    0.07
    (_)
    0.07
    _
    0.07
    Activations Density 0.060%

    No Known Activations