© 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. 19-RESID-POST-AA
    11. 102912
    Prev
    Next
    INDEX
    Explanations

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anum
    -0.09
     específico
    -0.09
    edevším
    -0.08
     तसे
    -0.08
     kanilang
    -0.08
     tertentu
    -0.08
     screamed
    -0.08
    aczego
    -0.07
     sekä
    -0.07
     Vielleicht
    -0.07
    POSITIVE LOGITS
     وبالتالي
    0.23
     waardoor
    0.16
     jolloin
    0.16
     sehingga
    0.16
     Consequently
    0.15
     so
    0.15
     ולכן
    0.15
    导致
    0.15
     sodass
    0.14
     consequently
    0.14
    Activations Density 0.063%

    No Known Activations