© 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. 70747
    Prev
    Next
    INDEX
    Explanations

    Physical activity and injuries

    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
     ఆట
    -0.08
     ప్రేక్షక
    -0.08
     misery
    -0.08
     publicados
    -0.08
     мез
    -0.08
     ప్రభుత్వ
    -0.08
     Huge
    -0.08
    entlicht
    -0.08
     hype
    -0.08
     burnout
    -0.08
    POSITIVE LOGITS
     truyền
    0.08
     CAD
    0.08
    rechter
    0.07
     CFA
    0.07
    -camera
    0.07
    等
    0.07
    Painter
    0.07
     tasks
    0.07
     cashier
    0.07
     Salesforce
    0.07
    Activations Density 0.013%

    No Known Activations