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. 13037
    Prev
    Next
    INDEX
    Explanations

    Inception

    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
     electronic
    -0.08
     ECO
    -0.08
     کب
    -0.07
    総
    -0.07
     biy
    -0.07
    _picture
    -0.07
    pygame
    -0.07
    电子
    -0.07
    Electronic
    -0.07
     Boxer
    -0.07
    POSITIVE LOGITS
     famously
    0.09
    팀
    0.08
    Manip
    0.08
     guarded
    0.08
    Manipulator
    0.08
    'équipe
    0.08
     recursively
    0.08
     prerequisite
    0.08
     Manip
    0.08
    edir
    0.08
    Activations Density 0.002%

    No Known Activations