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. 43763
    Prev
    Next
    INDEX
    Explanations

    reasoning

    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
    ازي
    -0.08
    _between
    -0.07
     τα
    -0.07
     Зам
    -0.07
     kæ
    -0.07
     stelt
    -0.07
     Пр
    -0.07
    ənd
    -0.07
     ваз
    -0.07
     பிர
    -0.07
    POSITIVE LOGITS
    Skill
    0.08
    842
    0.07
    Ball
    0.07
     BALL
    0.07
    CRI
    0.07
     tertiary
    0.07
     autofocus
    0.07
    apur
    0.07
     insign
    0.07
     secondary
    0.07
    Activations Density 0.549%

    No Known Activations