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. 111846
    Prev
    Next
    INDEX
    Explanations

    irregular word forms

    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
     densely
    -0.08
    MODULE
    -0.08
     koa
    -0.07
    <Web
    -0.07
    Contacts
    -0.07
    Present
    -0.07
    -present
    -0.07
     krist
    -0.07
    <B
    -0.07
     community
    -0.07
    POSITIVE LOGITS
     tane
    0.08
    nections
    0.08
    .processor
    0.08
     убрать
    0.08
     deň
    0.08
    ugeot
    0.08
     Courage
    0.08
     жылы
    0.08
     getenv
    0.08
     analisar
    0.07
    Activations Density 0.002%

    No Known Activations