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. 56090
    Prev
    Next
    INDEX
    Explanations

    Leading groups

    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
    Detailed
    -0.08
    ,就是
    -0.08
    銀
    -0.08
    .Reset
    -0.08
    bewertungen
    -0.07
    -Angeb
    -0.07
     anmeldelser
    -0.07
    _FIRE
    -0.07
    ETHER
    -0.07
    ismes
    -0.07
    POSITIVE LOGITS
    负责人
    0.13
     специалист
    0.11
     experts
    0.11
     novice
    0.11
     নেতা
    0.11
     residents
    0.10
    高手
    0.10
    管理员
    0.10
     Administrator
    0.10
    达人
    0.10
    Activations Density 0.325%

    No Known Activations