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. 12028
    Prev
    Next
    INDEX
    Explanations

    TF-IDF calculations

    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
    ophe
    -0.08
    فيات
    -0.08
    ériel
    -0.08
     thyroid
    -0.08
     établissements
    -0.08
    േശ
    -0.07
     Serg
    -0.07
     cytok
    -0.07
     mada
    -0.07
     wavelengths
    -0.07
    POSITIVE LOGITS
    -delay
    0.08
     크
    0.08
    Catal
    0.08
    이
    0.08
    너
    0.07
    _MM
    0.07
    -metal
    0.07
    _mar
    0.07
    _fc
    0.07
    িন্দ
    0.07
    Activations Density 0.000%

    No Known Activations