© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1469
    Prev
    Next
    INDEX
    Explanations

    system

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     populous
    -0.08
    APIView
    -0.08
     ress
    -0.08
    -taking
    -0.08
    察
    -0.08
     verzoek
    -0.08
    cljs
    -0.08
     midpoint
    -0.08
     Helpful
    -0.07
    session
    -0.07
    POSITIVE LOGITS
     Ti
    0.09
     تجهيز
    0.09
     hoses
    0.09
     ultrasonic
    0.09
     Logitech
    0.08
     система
    0.08
    升级
    0.08
    0.08
     malfunction
    0.08
     upgraded
    0.08
    Activations Density 0.017%
    No Known Activations