© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 63640
    Prev
    Next
    INDEX
    Explanations

    correction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unexpected
    -0.08
     Pew
    -0.08
    Nv
    -0.08
     =================================================================
    -0.08
    -0.07
    פת
    -0.07
    ijd
    -0.07
    ટ
    -0.07
    就在
    -0.07
    zienswaard
    -0.07
    POSITIVE LOGITS
     защиты
    0.10
    Protect
    0.10
     слова
    0.09
     Wörter
    0.09
    protect
    0.09
     ضد
    0.09
     защищ
    0.09
     protects
    0.08
     parole
    0.08
    Invisible
    0.08
    Activations Density 0.001%
    No Known Activations