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. 11-RESID-POST-AA
    6. 58587
    Prev
    Next
    INDEX
    Explanations

    :

    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
     outfit
    -0.08
     Dü
    -0.07
     donkey
    -0.07
    Dup
    -0.07
     Raider
    -0.07
     pout
    -0.07
    _duplicate
    -0.07
     tomb
    -0.07
    .In
    -0.07
     Berg
    -0.07
    POSITIVE LOGITS
     alam
    0.08
     جميلة
    0.08
     cleaner
    0.08
     aasta
    0.07
    ampi
    0.07
    :VC
    0.07
     talu
    0.07
     corret
    0.07
    bh
    0.07
     amis
    0.07
    Activations Density 0.001%

    No Known Activations