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. 19140
    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
     properties
    -0.08
     diverse
    -0.08
     eigenschappen
    -0.08
    ीय
    -0.07
     that
    -0.07
    601
    -0.07
    ी
    -0.07
     both
    -0.07
     high
    -0.07
    19
    -0.07
    POSITIVE LOGITS
     además
    0.09
     Zusätzlich
    0.09
    ROAD
    0.08
    ^{-
    0.08
    Invert
    0.08
     Subsequently
    0.08
     posteriormente
    0.08
     Heater
    0.08
     Además
    0.08
     Vapor
    0.08
    Activations Density 0.010%

    No Known Activations