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. 98550
    Prev
    Next
    INDEX
    Explanations

    Code diagrams

    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
     slu
    -0.08
     Destiny
    -0.08
     voeren
    -0.08
    粉嫩
    -0.07
    /Foundation
    -0.07
     futur
    -0.07
    âteau
    -0.07
    Pel
    -0.07
    spann
    -0.07
     предлагаем
    -0.07
    POSITIVE LOGITS
    ←
    0.10
     feedback
    0.08
    Feedback
    0.08
     nourishment
    0.08
     receptive
    0.08
    -most
    0.08
    432
    0.07
    -feedback
    0.07
    feedback
    0.07
    反馈
    0.07
    Activations Density 0.003%

    No Known Activations