© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 75612
    Prev
    Next
    INDEX
    Explanations

    plus symbol

    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
     негатив
    -0.08
    ਨ੍ਹਾਂ
    -0.08
    отр
    -0.08
     underpin
    -0.08
     rur
    -0.08
    *)(
    -0.08
    -0.08
    րանք
    -0.08
    Важно
    -0.07
    *>(&
    -0.07
    POSITIVE LOGITS
     increments
    0.09
    _INCREMENT
    0.09
     incremental
    0.09
     increment
    0.09
    crements
    0.08
     Increment
    0.08
     dam
    0.08
    .increment
    0.08
     incremento
    0.08
    Increment
    0.08
    Activations Density 0.006%
    No Known Activations