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. 78709
    Prev
    Next
    INDEX
    Explanations

    alcohol

    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
     brill
    -0.08
     βά
    -0.08
    iate
    -0.08
     Pig
    -0.08
     ضلع
    -0.08
    יקער
    -0.07
     Rao
    -0.07
     especí
    -0.07
    sges
    -0.07
     refrigeration
    -0.07
    POSITIVE LOGITS
     सेवन
    0.08
     intake
    0.08
     emotionally
    0.08
    在人
    0.08
     uống
    0.08
     anecd
    0.07
     insecurity
    0.07
    /AIDS
    0.07
    .loads
    0.07
    Corpus
    0.07
    Activations Density 0.009%

    No Known Activations