© 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. 12822
    Prev
    Next
    INDEX
    Explanations

    觉

    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
     isle
    -0.08
    netic
    -0.07
     anemia
    -0.07
     গত
    -0.07
    ов
    -0.07
     меди
    -0.07
    tfoot
    -0.07
     بیشتری
    -0.07
     έν
    -0.07
    нист
    -0.07
    POSITIVE LOGITS
     Tod
    0.08
     brutality
    0.08
     السلطة
    0.08
     Balm
    0.07
     Milli
    0.07
     gå
    0.07
     sass
    0.07
    ประมาณ
    0.07
    ുണ്ട്
    0.07
    લાક
    0.07
    Activations Density 0.009%

    No Known Activations