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. 101346
    Prev
    Next
    INDEX
    Explanations

    above

    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
     distr
    -0.08
    대로
    -0.08
     dex
    -0.08
     Zheng
    -0.08
     Jie
    -0.07
    acters
    -0.07
    מור
    -0.07
    (chan
    -0.07
     fate
    -0.07
     nif
    -0.07
    POSITIVE LOGITS
    ਆ
    0.08
    हे
    0.08
     allem
    0.08
     Robin
    0.07
     Brink
    0.07
    /off
    0.07
     demais
    0.07
     للت
    0.07
     Herm
    0.07
     ਆ
    0.07
    Activations Density 0.025%

    No Known Activations