© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 31300
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     embossed
    -0.07
     dupla
    -0.07
     Animated
    -0.07
    难
    -0.07
     believed
    -0.07
     articulated
    -0.07
     specifieke
    -0.07
     externa
    -0.07
     निर्द
    -0.07
     coupled
    -0.07
    POSITIVE LOGITS
     دستگاه
    0.08
     ўсе
    0.08
     ابزار
    0.08
     الدولة
    0.08
     فناوری
    0.08
    /day
    0.08
     قم
    0.08
    /year
    0.08
     مراج
    0.08
     הסת
    0.08
    Activations Density 0.034%

    No Known Activations