Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 417
    Prev
    Next
    INDEX
    Explanations

    math and logic problems

    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
     Holly
    -0.09
     hens
    -0.08
     FER
    -0.07
     kes
    -0.07
    voire
    -0.07
     інформа
    -0.07
    \Validator
    -0.07
    /th
    -0.07
     acha
    -0.07
     тим
    -0.07
    POSITIVE LOGITS
     Barra
    0.08
     originals
    0.07
    fair
    0.07
     Slam
    0.07
    AUTHOR
    0.07
     tats
    0.07
    Ja
    0.07
     Zan
    0.07
     aficionados
    0.07
    Ka
    0.07
    Activations Density 0.697%

    No Known Activations