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. 119404
    Prev
    Next
    INDEX
    Explanations

    library

    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
     europea
    -0.08
     رسان
    -0.08
     достига
    -0.08
     чара
    -0.08
     QS
    -0.08
     действие
    -0.08
     peuple
    -0.08
     Europé
    -0.07
     Axel
    -0.07
     نتي
    -0.07
    POSITIVE LOGITS
    .Builder
    0.09
    maybe
    0.08
    gui
    0.08
    .org
    0.08
     pertinentes
    0.08
    Specs
    0.07
     instalações
    0.07
    solid
    0.07
     instalaciones
    0.07
    と思
    0.07
    Activations Density 0.023%

    No Known Activations