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. 111830
    Prev
    Next
    INDEX
    Explanations

    Shifting access or availability

    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
    grese
    -0.08
    ihen
    -0.07
    armon
    -0.07
     Confer
    -0.07
    gev
    -0.07
    ELLOW
    -0.07
    trent
    -0.07
    kj
    -0.07
    几点
    -0.07
     epä
    -0.07
    POSITIVE LOGITS
     traditionally
    0.11
     traditionnel
    0.10
     Traditionally
    0.09
     التقلي
    0.09
    utari
    0.08
    زمات
    0.08
     روایت
    0.08
    Trad
    0.08
     exclusivement
    0.08
     منا
    0.08
    Activations Density 0.095%

    No Known Activations