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. 101644
    Prev
    Next
    INDEX
    Explanations

    horizontal

    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
    春节
    -0.08
    ご了承
    -0.08
     lauf
    -0.08
     Wenn
    -0.08
     할인
    -0.07
     Jes
    -0.07
    ڪن
    -0.07
    ”和
    -0.07
     byose
    -0.07
    绪
    -0.07
    POSITIVE LOGITS
     purely
    0.08
     khusus
    0.08
     pure
    0.08
     upward
    0.08
     tarik
    0.08
     perpendicular
    0.07
     вверх
    0.07
    /non
    0.07
     simply
    0.07
    ency
    0.07
    Activations Density 0.019%

    No Known Activations