© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 94509
    Prev
    Next
    INDEX
    Explanations

    rotate

    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
    细
    -0.07
     aggregation
    -0.07
    .Custom
    -0.07
     advisory
    -0.07
     idi
    -0.07
     hien
    -0.07
    (metadata
    -0.07
     Philosoph
    -0.07
     customization
    -0.07
     દેખ
    -0.07
    POSITIVE LOGITS
     revolve
    0.09
    <img
    0.09
    images
    0.09
     relocating
    0.08
    -images
    0.08
     зерк
    0.08
    rump
    0.08
     मेर
    0.08
    mirror
    0.08
    roen
    0.08
    Activations Density 0.018%

    No Known Activations