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

    Neuronpedia

    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. 1031
    Prev
    Next
    INDEX
    Explanations

    import

    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
     hairstyles
    -0.09
     hairs
    -0.08
     mother's
    -0.08
     במקרה
    -0.08
     unaffected
    -0.08
     Minus
    -0.07
    ISTIC
    -0.07
     hairstyle
    -0.07
    dismiss
    -0.07
     comprised
    -0.07
    POSITIVE LOGITS
     flujo
    0.08
     setuptools
    0.08
     Workflow
    0.08
    0.08
     herramientas
    0.08
     fluxo
    0.07
    .io
    0.07
     Hop
    0.07
    .*;↵
    0.07
     Config
    0.07
    Activations Density 0.008%
    No Known Activations