© 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. 11-RESID-POST-AA
    11. 8055
    Prev
    Next
    INDEX
    Explanations

    total

    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
     LES
    -0.07
    تهم
    -0.07
     Esk
    -0.07
     considér
    -0.07
     eu
    -0.07
     MAD
    -0.07
    ریشن
    -0.07
    _nd
    -0.07
     computations
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    emente
    0.09
    ination
    0.08
     Werk
    0.08
    iming
    0.08
     Fritz
    0.07
     Beginners
    0.07
     irony
    0.07
    imed
    0.07
     Abd
    0.07
     holistic
    0.07
    Activations Density 0.023%

    No Known Activations