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. 76094
    Prev
    Next
    INDEX
    Explanations

    loom

    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
     welfare
    -0.08
    chrij
    -0.07
     corretamente
    -0.07
    เน
    -0.07
     wrongly
    -0.07
     tiden
    -0.07
    -0.07
     대해서
    -0.07
    机构
    -0.07
     påvir
    -0.07
    POSITIVE LOGITS
    .te
    0.09
     exagger
    0.08
     München
    0.08
     đa
    0.08
    ipse
    0.08
     biodiversity
    0.08
     variedades
    0.07
     Mongolia
    0.07
     Bloomington
    0.07
     Purple
    0.07
    Activations Density 0.001%

    No Known Activations