Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76389
    Prev
    Next
    INDEX
    Explanations

    {

    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
     gird
    -0.08
     crosses
    -0.07
     RK
    -0.07
    orte
    -0.07
     Leb
    -0.07
     Анд
    -0.07
    家的
    -0.07
     fundamental
    -0.07
     mì
    -0.07
     I
    -0.07
    POSITIVE LOGITS
     terdiri
    0.09
     harms
    0.09
     ഭാഗമായി
    0.08
     കുറ്റ
    0.08
     friv
    0.08
     ഖ
    0.08
     gồm
    0.08
     പക്ഷ
    0.08
    acles
    0.08
    അ
    0.07
    Activations Density 0.000%

    No Known Activations