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. 120166
    Prev
    Next
    INDEX
    Explanations

    writing style guidelines

    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
     ressemble
    -0.09
     pourrez
    -0.08
    #pragma
    -0.08
     ressembl
    -0.08
     Estas
    -0.07
    렴
    -0.07
     traverse
    -0.07
     regarded
    -0.07
     diagnóstico
    -0.07
     luces
    -0.07
    POSITIVE LOGITS
     spelling
    0.12
     spelled
    0.11
    atex
    0.09
    文字
    0.09
     handwritten
    0.09
     লেখা
    0.09
     english
    0.09
     中文
    0.09
     فارسی
    0.09
     letter
    0.08
    Activations Density 0.034%

    No Known Activations