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. 98341
    Prev
    Next
    INDEX
    Explanations

    Place names

    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
     enrollment
    -0.08
    ેન
    -0.07
    __.
    -0.07
     mobs
    -0.07
     dwell
    -0.07
    .utils
    -0.07
     ciò
    -0.07
     appar
    -0.07
    868
    -0.07
     parses
    -0.07
    POSITIVE LOGITS
    yed
    0.09
    produkt
    0.09
     suspensión
    0.08
    ęs
    0.08
    uspended
    0.08
    gypt
    0.08
    ırı
    0.08
    producto
    0.07
     Saat
    0.07
     suspensão
    0.07
    Activations Density 0.001%

    No Known Activations