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. 52930
    Prev
    Next
    INDEX
    Explanations

    in

    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
     Victor
    -0.07
    疫
    -0.07
     �
    -0.07
     Genes
    -0.07
    fatt
    -0.07
    癌
    -0.07
     文件
    -0.07
     prolific
    -0.07
     genes
    -0.07
    POSITIVE LOGITS
     titul
    0.10
    .Sleep
    0.09
     σκο
    0.09
    Sleeping
    0.08
    _sleep
    0.08
    achine
    0.08
    /template
    0.08
     другую
    0.08
     descansar
    0.08
    ট
    0.08
    Activations Density 0.000%

    No Known Activations