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. 87918
    Prev
    Next
    INDEX
    Explanations

    equal sign

    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
     placebo
    -0.09
    -0.08
    Translations
    -0.07
     vape
    -0.07
     lumi
    -0.07
     receptor
    -0.07
     co
    -0.07
     tape
    -0.07
    tiny
    -0.07
     glory
    -0.06
    POSITIVE LOGITS
    manın
    0.09
    Jos
    0.09
    olves
    0.09
     aldus
    0.09
    大全
    0.09
     男
    0.08
     Jos
    0.08
    לץ
    0.08
     Milch
    0.08
    zocht
    0.08
    Activations Density 0.033%

    No Known Activations