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. 43337
    Prev
    Next
    INDEX
    Explanations

    ISO

    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
     clar
    -0.08
     compét
    -0.08
     gi
    -0.08
    KC
    -0.07
     competencia
    -0.07
     clarify
    -0.07
    -0.07
     SWOT
    -0.07
     basin
    -0.07
    naire
    -0.07
    POSITIVE LOGITS
     cooked
    0.10
     제작
    0.09
     Verte
    0.08
    _disk
    0.08
    .download
    0.08
    烧
    0.08
     vervaard
    0.08
     Hund
    0.08
    ന്തര
    0.08
    oworld
    0.08
    Activations Density 0.001%

    No Known Activations