© 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. 79102
    Prev
    Next
    INDEX
    Explanations

    button disable/enable state

    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
     agrad
    -0.08
     ADR
    -0.08
    世界
    -0.08
     David
    -0.07
     Dios
    -0.07
     प्रसिद्ध
    -0.07
     herald
    -0.07
    oub
    -0.07
     गौर
    -0.07
     obligations
    -0.07
    POSITIVE LOGITS
    .disabled
    0.14
     disabled
    0.13
    disabled
    0.13
     disables
    0.13
     Disabled
    0.12
     disable
    0.11
    (enabled
    0.11
     禁
    0.11
     clickable
    0.11
    .enabled
    0.11
    Activations Density 0.006%

    No Known Activations