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. 11607
    Prev
    Next
    INDEX
    Explanations

    CRM

    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
     denim
    -0.09
     milli
    -0.08
    CUT
    -0.08
     sesame
    -0.08
    ändige
    -0.08
    寺
    -0.08
    ston
    -0.08
    ôtes
    -0.08
    azar
    -0.08
    ítő
    -0.07
    POSITIVE LOGITS
     시스템
    0.12
     systems
    0.11
     системы
    0.11
     системе
    0.09
     प्रणाली
    0.09
     सिस्टम
    0.09
     ವ್ಯವಸ್ಥ
    0.09
    系统
    0.09
    Systems
    0.09
     систему
    0.09
    Activations Density 0.011%

    No Known Activations