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. 15-RESID-POST-AA
    6. 19240
    Prev
    Next
    INDEX
    Explanations

    one

    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
     charcoal
    -0.07
     longer
    -0.07
     contend
    -0.07
     drag
    -0.07
     tagged
    -0.07
     along
    -0.07
     tecn
    -0.07
     ket
    -0.07
    .rename
    -0.07
     Chevron
    -0.07
    POSITIVE LOGITS
    _DATA
    0.09
     Diet
    0.08
     Data
    0.08
    RFC
    0.08
    _GAME
    0.08
    financial
    0.08
     Financial
    0.08
     वित्त
    0.08
     Đại
    0.08
    NZ
    0.08
    Activations Density 0.011%

    No Known Activations