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. 45204
    Prev
    Next
    INDEX
    Explanations

    tax loss carryforward

    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
     تحقیق
    -0.09
     দায়িত্ব
    -0.09
    heim
    -0.08
     bricol
    -0.08
     연구
    -0.08
     재미
    -0.08
     YMCA
    -0.08
    Coffee
    -0.07
    coordinates
    -0.07
     dieting
    -0.07
    POSITIVE LOGITS
    нын
    0.08
    ,use
    0.08
     unused
    0.08
    移
    0.08
     offset
    0.07
     isticma
    0.07
     insolv
    0.07
     waardoor
    0.07
    maxcdn
    0.07
     reductions
    0.07
    Activations Density 0.004%

    No Known Activations