© 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. 102338
    Prev
    Next
    INDEX
    Explanations

    functionality in different languages

    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
     citing
    -0.09
     uygun
    -0.09
    .Elements
    -0.08
     روایت
    -0.08
     remained
    -0.08
     ί
    -0.08
     məsəl
    -0.08
     ως
    -0.08
     ahol
    -0.08
     onbe
    -0.08
    POSITIVE LOGITS
     functionality
    0.22
    功能
    0.20
     يقوم
    0.19
     기능
    0.19
     수행
    0.19
     выполня
    0.18
     funcionalidades
    0.17
     عملکرد
    0.17
     melakukan
    0.17
     функцион
    0.17
    Activations Density 0.023%

    No Known Activations