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. 19265
    Prev
    Next
    INDEX
    Explanations

    foreign word pieces

    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
     (
    -0.08
     simplifying
    -0.08
    (
    -0.07
    :↵↵
    -0.07
     interpolation
    -0.07
     simpl
    -0.07
    াল
    -0.07
     prevention
    -0.07
     preservatives
    -0.07
    ,
    -0.07
    POSITIVE LOGITS
    _instances
    0.10
     укра
    0.09
     кім
    0.09
    Instances
    0.09
    усан
    0.09
     cracked
    0.09
     rame
    0.09
     særlig
    0.09
    uleke
    0.09
     cerve
    0.09
    Activations Density 0.133%

    No Known Activations