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. 48477
    Prev
    Next
    INDEX
    Explanations

    实现

    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
    lery
    -0.09
     لگ
    -0.08
     Chow
    -0.08
    কর
    -0.07
    ôr
    -0.07
    kampf
    -0.07
    사항
    -0.07
     varten
    -0.07
     datum
    -0.07
     особен
    -0.07
    POSITIVE LOGITS
    全面
    0.09
     seamless
    0.09
    ắp
    0.08
     coexist
    0.08
     facets
    0.08
     istedi
    0.08
     reducción
    0.07
     France
    0.07
     Paris
    0.07
     comprehensive
    0.07
    Activations Density 0.009%

    No Known Activations