© 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. 78792
    Prev
    Next
    INDEX
    Explanations

    el

    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
     WIB
    -0.08
    -0.07
    იტ
    -0.07
    672
    -0.07
     Kindergarten
    -0.07
     Hana
    -0.07
    uitar
    -0.07
    EY
    -0.07
    isbn
    -0.07
     Ballet
    -0.07
    POSITIVE LOGITS
    κά
    0.07
     pinpoint
    0.07
    лі
    0.07
     bitter
    0.07
     arranc
    0.07
     creepy
    0.07
     odpor
    0.07
    ivic
    0.07
     scenic
    0.07
     النهاية
    0.07
    Activations Density 0.001%
    No Known Activations