Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112282
    Prev
    Next
    INDEX
    Explanations

    equals sign

    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
    ابه
    -0.09
     acción
    -0.08
    =D
    -0.08
    Copper
    -0.08
     Hazard
    -0.07
    Haz
    -0.07
     Copper
    -0.07
     defining
    -0.07
     الطلب
    -0.07
     hospitality
    -0.07
    POSITIVE LOGITS
     leva
    0.08
    /root
    0.08
     vidare
    0.08
    ritic
    0.08
    .y
    0.08
    润
    0.08
     kaha
    0.08
     fête
    0.08
    (Collections
    0.08
    elha
    0.08
    Activations Density 0.074%

    No Known Activations