Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60940
    Prev
    Next
    INDEX
    Explanations

    recom

    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
     Kobe
    -0.09
     flea
    -0.08
     freeze
    -0.08
    freeze
    -0.08
     crab
    -0.08
     ಹೇಳ
    -0.07
     TA
    -0.07
    SSC
    -0.07
     statements
    -0.07
     terb
    -0.07
    POSITIVE LOGITS
     बित
    0.08
    Simpl
    0.08
     الموضوع
    0.07
     הלא
    0.07
    旧
    0.07
    umper
    0.07
     urgente
    0.07
     desperately
    0.07
    Sparse
    0.07
     domicili
    0.07
    Activations Density 0.001%

    No Known Activations