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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30869
    Prev
    Next
    INDEX
    Explanations

    pass through

    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
     מקצוע
    -0.08
     במהלך
    -0.08
     תוך
    -0.08
     fade
    -0.08
     GIF
    -0.08
    �
    -0.08
     Fade
    -0.08
    腕
    -0.08
     //--
    -0.08
     کا
    -0.08
    POSITIVE LOGITS
     filings
    0.09
    -existing
    0.07
     cannabinoids
    0.07
     distributions
    0.07
     domicile
    0.07
     diária
    0.07
     exporter
    0.07
    living
    0.07
    산
    0.07
     exporters
    0.07
    Activations Density 0.006%

    No Known Activations