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. 58763
    Prev
    Next
    INDEX
    Explanations

    til

    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
     réserve
    -0.08
    ytt
    -0.08
    -0.07
    Boost
    -0.07
     reserva
    -0.07
     interface
    -0.07
     borrowers
    -0.07
    Older
    -0.07
     latch
    -0.07
     amplification
    -0.07
    POSITIVE LOGITS
     tess
    0.10
     paintings
    0.09
     repeating
    0.08
     endlessly
    0.08
    ACP
    0.08
    在線
    0.08
    Shapes
    0.08
     سهم
    0.08
     нанес
    0.08
     चित्र
    0.08
    Activations Density 0.004%

    No Known Activations