© 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. 3-RESID-POST-AA
    11. 2740
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     পাশ
    -0.09
    ュー
    -0.08
     mond
    -0.08
     jurídico
    -0.08
     случаи
    -0.08
     keenya
    -0.08
     які
    -0.08
     заявления
    -0.07
     produtividade
    -0.07
     дог
    -0.07
    POSITIVE LOGITS
     complex
    0.08
     Eg
    0.08
    complex
    0.07
     Aggreg
    0.07
     nutrients
    0.07
    25
    0.07
     délic
    0.07
    ắp
    0.07
     Bip
    0.07
     Complex
    0.07
    Activations Density 0.002%

    No Known Activations