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. 78587
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    ‌ക
    -0.09
     crossover
    -0.08
     pilot
    -0.08
    Pilot
    -0.08
     Pilot
    -0.08
     Pel
    -0.08
    Contest
    -0.08
     fel
    -0.07
    Pros
    -0.07
     cardiovascular
    -0.07
    POSITIVE LOGITS
    �
    0.07
     opr
    0.07
     eat
    0.07
    ।
    0.07
     অন্ত
    0.07
    ”
    0.07
     Eat
    0.07
     behouden
    0.07
     হলে
    0.07
     seit
    0.07
    Activations Density 0.042%

    No Known Activations