© 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. 23-RESID-POST-AA
    11. 51355
    Prev
    Next
    INDEX
    Explanations

    Foreign languages

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ателю
    -0.18
    ation
    -0.18
    ательной
    -0.17
    ателям
    -0.17
    ательного
    -0.17
    ательная
    -0.17
    ательных
    -0.17
    ing
    -0.17
    атели
    -0.17
    атель
    -0.16
    POSITIVE LOGITS
    ु
    0.17
    ुओं
    0.16
    zyć
    0.16
    ্ছেন
    0.16
    ्व
    0.15
    ্তা
    0.15
    ು
    0.15
    ্ছ
    0.15
    ்வு
    0.15
    지는
    0.15
    Activations Density 0.466%

    No Known Activations