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. 43754
    Prev
    Next
    INDEX
    Explanations

    son

    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
     bn
    -0.08
     vorg
    -0.08
    argi
    -0.08
     mij
    -0.08
     faker
    -0.08
     bailout
    -0.07
     abu
    -0.07
     bubb
    -0.07
     abi
    -0.07
     उत्प
    -0.07
    POSITIVE LOGITS
     repose
    0.08
    قيقة
    0.08
    Nec
    0.07
    essoa
    0.07
     pomen
    0.07
    113
    0.07
    Boot
    0.07
    那么
    0.07
    hower
    0.07
    593
    0.07
    Activations Density 0.000%

    No Known Activations