© 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. 69288
    Prev
    Next
    INDEX
    Explanations

    chip

    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
    退款
    -0.08
     TX
    -0.08
     refund
    -0.08
    invalidate
    -0.08
    flash
    -0.08
     rembourse
    -0.08
     refunds
    -0.08
     speci
    -0.07
    ry
    -0.07
     refunded
    -0.07
    POSITIVE LOGITS
    律
    0.08
    /javase
    0.08
     Maur
    0.08
    깨
    0.07
     उम
    0.07
     Fix
    0.07
    达
    0.07
     SAP
    0.07
    驾驶
    0.07
    泊
    0.07
    Activations Density 0.001%

    No Known Activations