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. 43146
    Prev
    Next
    INDEX
    Explanations

    Vestal

    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
    KEY
    -0.08
     themes
    -0.08
     sulfur
    -0.07
     temperature
    -0.07
    ptable
    -0.07
     حول
    -0.07
    USER
    -0.07
     bubble
    -0.07
    _PRESENT
    -0.07
    pert
    -0.07
    POSITIVE LOGITS
     fiance
    0.09
    eyes
    0.09
    mad
    0.08
    ніч
    0.08
    найы
    0.08
    ್ನಾಟಕ
    0.08
     специальных
    0.08
     moatte
    0.08
    час
    0.08
    ítő
    0.08
    Activations Density 0.000%

    No Known Activations