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. 11746
    Prev
    Next
    INDEX
    Explanations

    Notifications

    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
     underway
    -0.08
     _,
    -0.07
    Proposal
    -0.07
    挂牌
    -0.07
     surveying
    -0.07
    schrijving
    -0.07
     üles
    -0.07
    }",↵
    -0.07
     učen
    -0.07
     %",↵
    -0.07
    POSITIVE LOGITS
    GING
    0.08
     حين
    0.08
     пить
    0.07
    ிட
    0.07
     ада
    0.07
     نع
    0.07
    estruct
    0.07
     provenientes
    0.07
     fútbol
    0.07
     Eccles
    0.07
    Activations Density 0.003%

    No Known Activations