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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21544
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ing
    -0.11
     overige
    -0.10
    その他
    -0.09
    ด้
    -0.09
    zelfde
    -0.09
     그대로
    -0.09
     andern
    -0.09
    ғы
    -0.09
    ẳ
    -0.09
    ույց
    -0.09
    POSITIVE LOGITS
    ojë
    0.08
     tribal
    0.07
    bage
    0.07
    ológico
    0.07
    bea
    0.07
    ebooks
    0.07
    ovní
    0.07
    0.07
    idaire
    0.07
     localização
    0.07
    Activations Density 0.009%
    No Known Activations