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

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 103191
    Prev
    Next
    INDEX
    Explanations

    Non-English and ":)"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bitrate
    -0.07
     IPV
    -0.07
    -II
    -0.07
     diplomatic
    -0.07
     диплом
    -0.07
    人民币
    -0.07
     diplomacy
    -0.07
    ுங்கள்
    -0.07
     były
    -0.07
    ­ment
    -0.07
    POSITIVE LOGITS
     مثال
    0.08
    :)↵
    0.08
     anyar
    0.07
     només
    0.07
    осу
    0.07
     اضاف
    0.07
     مستقل
    0.07
     исключительно
    0.07
     یوې
    0.07
    érée
    0.07
    Activations Density 0.000%

    No Known Activations