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. 119246
    Prev
    Next
    INDEX
    Explanations

    buffer

    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
     creation
    -0.08
     création
    -0.08
     geração
    -0.08
    790
    -0.08
    ుత
    -0.08
     creación
    -0.08
     génération
    -0.07
    892
    -0.07
    ئات
    -0.07
    creation
    -0.07
    POSITIVE LOGITS
     Ethics
    0.08
    :px
    0.08
     шту
    0.07
     Studie
    0.07
     തീരുമാനം
    0.07
     prv
    0.07
    )&&(
    0.07
    /am
    0.07
     filosof
    0.07
    Brief
    0.07
    Activations Density 0.001%

    No Known Activations