© 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. 11-RESID-POST-AA
    11. 78001
    Prev
    Next
    INDEX
    Explanations

    code

    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
     اعلام
    -0.08
    .object
    -0.08
     ره
    -0.08
    .vars
    -0.08
     أمام
    -0.08
    forced
    -0.08
    ужден
    -0.08
    heter
    -0.08
    Presenter
    -0.08
     kız
    -0.07
    POSITIVE LOGITS
    函数
    0.13
     함수
    0.12
     returns
    0.11
     utility
    0.11
     функция
    0.10
     функцию
    0.10
     Funktion
    0.10
     retorna
    0.09
     Utility
    0.09
     Returns
    0.09
    Activations Density 0.047%

    No Known Activations