© 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. 64060
    Prev
    Next
    INDEX
    Explanations

    should

    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
    itali
    -0.08
     شکار
    -0.08
     كبار
    -0.08
     تشكيل
    -0.08
     خلق
    -0.08
     कानून
    -0.08
    альних
    -0.08
    Hal
    -0.08
     مسب
    -0.08
     Ott
    -0.08
    POSITIVE LOGITS
    运行
    0.12
    正常
    0.11
     hopefully
    0.11
     успешно
    0.10
     successfully
    0.10
     정상
    0.10
     исправ
    0.10
    顺
    0.09
     podrás
    0.09
     ошибки
    0.09
    Activations Density 0.010%

    No Known Activations