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. 43496
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     greedy
    -0.09
    .Low
    -0.08
    老虎机
    -0.08
     greed
    -0.08
    亂
    -0.08
     퍼
    -0.08
    automater
    -0.07
    Believe
    -0.07
     Boga
    -0.07
     hogares
    -0.07
    POSITIVE LOGITS
     nautical
    0.08
     éditions
    0.08
     Ottoman
    0.07
     Socket
    0.07
     Valent
    0.07
     J
    0.07
     Abdel
    0.07
     Öz
    0.07
    ísk
    0.07
     jät
    0.07
    Activations Density 0.023%

    No Known Activations