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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 112528
    Prev
    Next
    INDEX
    Explanations

    Russia

    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
     Robinson
    -0.07
     المهمة
    -0.07
     legyen
    -0.07
     RAID
    -0.07
    Ù
    -0.07
     Optional
    -0.06
     ì
    -0.06
    ASP
    -0.06
    Rust
    -0.06
     consist
    -0.06
    POSITIVE LOGITS
    央视
    0.11
     qarşı
    0.10
     tərəfindən
    0.09
     propaganda
    0.09
     tomonidan
    0.09
    वीं
    0.09
    实力
    0.09
     fəali
    0.08
    ච
    0.08
    �
    0.08
    Activations Density 0.073%

    No Known Activations