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. 90323
    Prev
    Next
    INDEX
    Explanations

    Code and debugging

    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
     exemplary
    -0.08
     excessive
    -0.08
     khách
    -0.08
    -esque
    -0.08
     Kunden
    -0.07
     unparalleled
    -0.07
     olyan
    -0.07
     offer
    -0.07
     conseillé
    -0.07
     任
    -0.07
    POSITIVE LOGITS
     제대로
    0.15
    正确
    0.13
     correctement
    0.12
     properly
    0.11
     corretamente
    0.11
     correctly
    0.11
     correctamente
    0.11
    proper
    0.09
     सही
    0.09
     правильно
    0.09
    Activations Density 0.041%

    No Known Activations