© 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. 95355
    Prev
    Next
    INDEX
    Explanations

    TikTok

    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
     bearings
    -0.07
     comer
    -0.07
    AP
    -0.07
    21
    -0.07
    α
    -0.07
    *****
    -0.07
     electron
    -0.07
     qp
    -0.07
     பெய
    -0.07
     Circ
    -0.07
    POSITIVE LOGITS
     tutorials
    0.10
     filmed
    0.09
     Tok
    0.09
     फिल्म
    0.09
     Tutorials
    0.09
    教程
    0.09
     टिप
    0.08
     दिख
    0.08
     ogl
    0.08
     filming
    0.08
    Activations Density 0.023%

    No Known Activations