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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 117533
    Prev
    Next
    INDEX
    Explanations

    бы

    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
     व्यव
    -0.08
     Thanh
    -0.08
     rund
    -0.07
     जे
    -0.07
    BCD
    -0.07
    омина
    -0.07
    נית
    -0.07
     Beaches
    -0.07
    ------------------------------------------------------------------------------
    -0.07
    /help
    -0.07
    POSITIVE LOGITS
    gets
    0.09
     ওঠ
    0.08
     presto
    0.08
     excursion
    0.08
    0.07
     Nate
    0.07
     wildly
    0.07
     ni
    0.07
    нон
    0.07
    rough
    0.07
    Activations Density 0.004%

    No Known Activations