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. 11-RESID-POST-AA
    6. 43852
    Prev
    Next
    INDEX
    Explanations

    stoichiometry

    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
    RGCTXData
    -0.09
     embellished
    -0.08
     Wig
    -0.08
     zusamm
    -0.08
     adorned
    -0.08
    daş
    -0.08
    ृत्व
    -0.07
    .Index
    -0.07
     établi
    -0.07
    Carousel
    -0.07
    POSITIVE LOGITS
     limiting
    0.10
     最大
    0.10
     limiter
    0.09
    limited
    0.09
     leftovers
    0.09
    _LIMIT
    0.09
    shutdown
    0.09
     shutdown
    0.09
     limitada
    0.09
    aze
    0.09
    Activations Density 0.014%

    No Known Activations