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. 55813
    Prev
    Next
    INDEX
    Explanations

    combining characters

    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
     avenues
    -0.08
     বিশ
    -0.08
     conversion
    -0.07
    退出
    -0.07
     trade
    -0.07
    conversion
    -0.07
     reserves
    -0.07
     leisure
    -0.07
     Leisure
    -0.07
     lobby
    -0.07
    POSITIVE LOGITS
     표시
    0.11
    付き
    0.10
    Overlay
    0.10
     encima
    0.10
     overlays
    0.09
    bum
    0.09
     लगाने
    0.09
     underneath
    0.09
     BUR
    0.09
     rambut
    0.09
    Activations Density 0.006%

    No Known Activations