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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 64995
    Prev
    Next
    INDEX
    Explanations

    Sections or parts

    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
     clock
    -0.08
     kaart
    -0.08
    aston
    -0.07
     repreh
    -0.07
     свеж
    -0.07
     defended
    -0.07
     счит
    -0.07
     дик
    -0.07
     чрез
    -0.07
     yetiş
    -0.07
    POSITIVE LOGITS
     ഭാഗമായി
    0.10
    भाग
    0.10
    篇
    0.09
    上一篇
    0.09
     الجزء
    0.09
    หนึ่ง
    0.09
     Episode
    0.09
    Parte
    0.08
     Eta
    0.08
     Uno
    0.08
    Activations Density 0.041%

    No Known Activations