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. 112229
    Prev
    Next
    INDEX
    Explanations

    reading aloud

    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
     Metadata
    -0.08
     wallpapers
    -0.07
     Application
    -0.07
     Voucher
    -0.07
     wallpaper
    -0.07
     billed
    -0.07
     wyposaż
    -0.07
    巴
    -0.07
     safely
    -0.07
     Documentation
    -0.07
    POSITIVE LOGITS
     glaring
    0.09
     chắn
    0.09
     chưa
    0.09
     termos
    0.09
     upe
    0.09
    感じ
    0.09
     bothers
    0.09
     hiel
    0.09
     अस्प
    0.08
     quedado
    0.08
    Activations Density 0.013%

    No Known Activations