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. 8790
    Prev
    Next
    INDEX
    Explanations

    刻

    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
    334
    -0.08
    843
    -0.08
    502
    -0.08
    522
    -0.08
     wrongdoing
    -0.08
    貨
    -0.08
    544
    -0.08
    535
    -0.07
    644
    -0.07
     dies
    -0.07
    POSITIVE LOGITS
    理解
    0.19
     understanding
    0.18
     বুঝ
    0.18
    了解到
    0.18
    了解
    0.16
    Understanding
    0.15
     Understanding
    0.15
     understand
    0.15
     entender
    0.15
    认识
    0.15
    Activations Density 0.104%

    No Known Activations