© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 108673
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    。截至
    -0.09
     accelerator
    -0.09
     accelerating
    -0.09
     assembled
    -0.08
    采购
    -0.08
     GPU
    -0.08
     seafood
    -0.08
     الأرض
    -0.08
    Registrant
    -0.08
    寿
    -0.08
    POSITIVE LOGITS
     interpersonal
    0.15
     psychological
    0.14
    心理
    0.13
     calmly
    0.12
     психолог
    0.12
     politely
    0.12
    Emotion
    0.12
     etiquette
    0.11
     emotional
    0.11
     psychology
    0.11
    Activations Density 0.056%

    No Known Activations