Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 119381
    Prev
    Next
    INDEX
    Explanations

    or

    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
     Danke
    -0.08
     brachte
    -0.07
     хотелось
    -0.07
    /img
    -0.07
    ங்கே
    -0.07
     gracias
    -0.07
     благодаря
    -0.07
     এনে
    -0.07
    ვას
    -0.07
     díky
    -0.07
    POSITIVE LOGITS
    の場合
    0.11
    Eligible
    0.10
     Eligible
    0.10
     uitzonder
    0.09
     eligible
    0.09
     Eligibility
    0.09
     probation
    0.09
     Residential
    0.09
     ≤
    0.08
    eligible
    0.08
    Activations Density 0.105%

    No Known Activations