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. 12901
    Prev
    Next
    INDEX
    Explanations

    C programming arguments

    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
     Engl
    -0.09
     elim
    -0.08
     autonom
    -0.08
     elimin
    -0.08
    ologia
    -0.08
     تؤ
    -0.07
    ogl
    -0.07
     exclus
    -0.07
     confin
    -0.07
    馆
    -0.07
    POSITIVE LOGITS
     brave
    0.08
     giant
    0.07
    [sub
    0.07
     अधिकारी
    0.07
    Ios
    0.07
     વાયર
    0.07
     वायर
    0.07
     sien
    0.07
    .espresso
    0.07
     किश
    0.07
    Activations Density 0.001%

    No Known Activations