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. 42965
    Prev
    Next
    INDEX
    Explanations

    Goals and Development

    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
     spool
    -0.08
     মাঝে
    -0.08
     ttk
    -0.08
    rë
    -0.07
     rigs
    -0.07
    lac
    -0.07
    ંચ
    -0.07
    chmal
    -0.07
     styles
    -0.07
     দিলে
    -0.07
    POSITIVE LOGITS
     Goals
    0.11
     أهداف
    0.10
     goals
    0.10
    Goals
    0.10
     UNESCO
    0.09
     UNICEF
    0.09
    习近平
    0.09
     aspirations
    0.09
     slogan
    0.09
     poursu
    0.09
    Activations Density 0.007%

    No Known Activations