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. 43263
    Prev
    Next
    INDEX
    Explanations

    code/matrices/formulas

    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
     slog
    -0.08
    Trig
    -0.07
    ál
    -0.07
     tragedy
    -0.07
    locals
    -0.07
     student
    -0.07
    #.
    -0.07
    سې
    -0.07
    ર્જ
    -0.07
     sense
    -0.07
    POSITIVE LOGITS
     recipro
    0.09
    ият
    0.09
     Reciprocity
    0.09
     รู
    0.08
     เพล
    0.08
     reput
    0.08
    ifun
    0.08
     ความ
    0.08
     ดู
    0.08
     ועד
    0.08
    Activations Density 0.009%

    No Known Activations