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. 43789
    Prev
    Next
    INDEX
    Explanations

    字

    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
    Like
    -0.08
     elenco
    -0.07
     દરેક
    -0.07
    Plano
    -0.07
     resulted
    -0.07
    _dataframe
    -0.07
     લખ
    -0.07
    Heading
    -0.07
     apar
    -0.07
     induction
    -0.07
    POSITIVE LOGITS
    urch
    0.08
    atile
    0.08
    ********************************************************
    0.08
     Oui
    0.07
    winds
    0.07
    ifndef
    0.07
    isticated
    0.07
    0.07
    +,
    0.07
     drauf
    0.07
    Activations Density 0.000%

    No Known Activations