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. 74521
    Prev
    Next
    INDEX
    Explanations

    ur

    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
     spart
    -0.08
     �
    -0.08
    まり
    -0.07
    367
    -0.07
     unanimous
    -0.07
     premios
    -0.07
     dedication
    -0.07
     درست
    -0.07
     integrated
    -0.07
     dedi
    -0.07
    POSITIVE LOGITS
     headaches
    0.09
     logística
    0.08
     fata
    0.08
    น์
    0.08
     еңбек
    0.08
    очную
    0.08
    자동
    0.08
    그래
    0.08
     الفحم
    0.08
     commodities
    0.08
    Activations Density 0.000%

    No Known Activations