© 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. 129470
    Prev
    Next
    INDEX
    Explanations

    Code related

    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
     Rece
    -0.08
    ර
    -0.08
     roja
    -0.08
     crashes
    -0.07
     obliged
    -0.07
    olidays
    -0.07
    /'.
    -0.07
     disputes
    -0.07
     thị
    -0.07
    _drv
    -0.07
    POSITIVE LOGITS
     Spacer
    0.11
    Spacer
    0.09
     spacer
    0.09
    .arc
    0.08
    (amount
    0.08
     лице
    0.08
     выйти
    0.08
    براير
    0.08
    (System
    0.08
     паспорт
    0.08
    Activations Density 0.001%

    No Known Activations