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

    Neuronpedia

    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. 801
    Prev
    Next
    INDEX
    Explanations

    two

    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
    -0.08
     الخاص
    -0.08
     उपाय
    -0.08
     INCLUDE
    -0.08
    特色
    -0.08
     사항
    -0.08
    istu
    -0.08
     Augenmerk
    -0.08
     الجديد
    -0.07
    onik
    -0.07
    POSITIVE LOGITS
     birbir
    0.10
     തമ്മ
    0.08
     aparentemente
    0.08
     서로
    0.08
     commuting
    0.08
     imm
    0.08
     seemingly
    0.08
     mutually
    0.08
     Confer
    0.08
     друг
    0.07
    Activations Density 0.025%
    No Known Activations