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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 30597
    Prev
    Next
    INDEX
    Explanations

    open

    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
     hips
    -0.09
    portfolio
    -0.09
     Djokovic
    -0.08
    提示
    -0.08
     przyp
    -0.08
    wechat
    -0.08
     gebaseerd
    -0.08
     %{
    -0.08
     exager
    -0.08
    gyro
    -0.08
    POSITIVE LOGITS
     fopen
    0.11
     opened
    0.10
    打开
    0.10
    .open
    0.10
     reopened
    0.09
     읽
    0.09
     القراءة
    0.09
     فتح
    0.09
     lectura
    0.09
    (IOException
    0.09
    Activations Density 0.013%

    No Known Activations