© 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. 2599
    Prev
    Next
    INDEX
    Explanations

    Forge

    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
    ứ
    -0.07
    ประ
    -0.07
    راز
    -0.07
     revisions
    -0.07
    FIN
    -0.07
     onc
    -0.07
    चर
    -0.07
     teléfono
    -0.07
    Grades
    -0.07
     Venet
    -0.07
    POSITIVE LOGITS
     Sad
    0.08
     cactus
    0.08
     discut
    0.08
    /render
    0.07
    -output
    0.07
     dune
    0.07
    える
    0.07
     Nay
    0.07
    0.07
     Sama
    0.07
    Activations Density 0.002%
    No Known Activations