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. 77442
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     NHS
    -0.08
     pathways
    -0.08
    ijn
    -0.08
    amilton
    -0.07
    .android
    -0.07
    dotenv
    -0.07
     }
    ↵
    ↵
    ↵
    ↵
    -0.07
     ud
    -0.07
     },↵↵↵
    -0.07
    失
    -0.07
    POSITIVE LOGITS
     Regl
    0.08
    arko
    0.08
    0.07
    >Main
    0.07
     eaux
    0.07
    ownik
    0.07
    @Controller
    0.07
    mani
    0.07
    ният
    0.07
    оложение
    0.07
    Activations Density 0.006%

    No Known Activations