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. 15-RESID-POST-AA
    6. 19123
    Prev
    Next
    INDEX
    Explanations

    (-

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     complete
    -0.09
     पूरा
    -0.08
     secret
    -0.08
     ملي
    -0.08
     the
    -0.08
     total
    -0.08
     fluffy
    -0.08
     visc
    -0.07
     floppy
    -0.07
     completa
    -0.07
    POSITIVE LOGITS
    toggle
    0.10
    Toggle
    0.10
    ^{-
    0.09
    ^{
    0.08
    াফল
    0.08
    ^\
    0.08
    -toggle
    0.08
     Toggle
    0.08
    ^-
    0.08
    boolean
    0.08
    Activations Density 0.005%

    No Known Activations