© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 26093
    Prev
    Next
    INDEX
    Explanations

    car

    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
    <typename
    -0.08
     الشكل
    -0.08
     liger
    -0.07
     scorching
    -0.07
     الإنجليزية
    -0.07
     stitched
    -0.07
     حالة
    -0.07
     इंग
    -0.07
     Appar
    -0.07
    isiert
    -0.07
    POSITIVE LOGITS
     Lol
    0.08
     hacemos
    0.08
     đa
    0.08
    اسو
    0.08
     zagot
    0.07
     �
    0.07
     күп
    0.07
     консульт
    0.07
     hafi
    0.07
     куб
    0.07
    Activations Density 0.001%

    No Known Activations