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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98401
    Prev
    Next
    INDEX
    Explanations

    line

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    folders
    -0.08
    -www
    -0.07
     tonnes
    -0.07
     skins
    -0.07
    textures
    -0.07
    chemas
    -0.07
     ویل
    -0.07
    (pkg
    -0.07
    џ
    -0.07
    ingtones
    -0.07
    POSITIVE LOGITS
     line
    0.74
    Line
    0.68
    _line
    0.67
    	line
    0.67
     Line
    0.67
    .line
    0.66
     लाइन
    0.64
    (line
    0.64
    line
    0.61
    _LINE
    0.61
    Activations Density 0.621%

    No Known Activations