© 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 EvalsExportsinterp-engineNEWAPI 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. 70279
    Prev
    Next
    INDEX
    Explanations

    playgrounds

    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
     receipts
    -0.10
     unem
    -0.09
    骤
    -0.09
     forecasts
    -0.09
     marriages
    -0.08
     ntx
    -0.08
     contratos
    -0.08
     wena
    -0.08
     ABI
    -0.08
     strak
    -0.08
    POSITIVE LOGITS
    设施
    0.10
    featured
    0.09
    invite
    0.08
    stacle
    0.08
     diversão
    0.08
     playground
    0.08
     loot
    0.08
    safe
    0.08
     themed
    0.08
     diversión
    0.08
    Activations Density 0.023%

    No Known Activations