Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 106147
    Prev
    Next
    INDEX
    Explanations

    C++ iomanip library

    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
    斗
    -0.09
     ed
    -0.08
     联系
    -0.08
     fes
    -0.08
     intelligence
    -0.07
    智
    -0.07
    英雄
    -0.07
    研究
    -0.07
     Ö
    -0.07
    联系
    -0.07
    POSITIVE LOGITS
    iomanip
    0.12
     setw
    0.10
    opacity
    0.10
    endl
    0.09
     formatting
    0.09
     Formatting
    0.09
    setw
    0.09
    precision
    0.09
    Formatter
    0.09
    Changer
    0.09
    Activations Density 0.002%

    No Known Activations