© 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. 112550
    Prev
    Next
    INDEX
    Explanations

    Foreign languages and movie titles

    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
     Dek
    -0.09
    kab
    -0.08
     šte
    -0.08
     perhatian
    -0.08
     dégâts
    -0.08
     शाख
    -0.07
    Dek
    -0.07
     dekor
    -0.07
    ೇರಿ
    -0.07
    lied
    -0.07
    POSITIVE LOGITS
     referred
    0.09
     appendix
    0.08
     Appendix
    0.07
    0.07
    符合
    0.07
    0.07
     from
    0.07
    .exe
    0.07
     مطلوب
    0.07
     onverw
    0.07
    Activations Density 0.000%
    No Known Activations