© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2778
    Prev
    Next
    INDEX
    Explanations

    Hä

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fend
    -0.08
    pure
    -0.08
    純
    -0.08
    ुद्ध
    -0.08
    pren
    -0.07
     parecia
    -0.07
     pure
    -0.07
     transmite
    -0.07
     immobilier
    -0.07
    BW
    -0.07
    POSITIVE LOGITS
    ٹر
    0.08
     خرید
    0.08
     اٹھ
    0.07
    _delivery
    0.07
    ROLLER
    0.07
     Princess
    0.07
     Siege
    0.07
    _cube
    0.07
    šenja
    0.07
    šenje
    0.07
    Activations Density 0.000%

    No Known Activations