© 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. 23-RESID-POST-AA
    11. 97792
    Prev
    Next
    INDEX
    Explanations

    Non-english code snippets

    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
     条
    -0.08
     emotionally
    -0.08
     condición
    -0.07
    条
    -0.07
     కాగా
    -0.07
     persönlichen
    -0.07
    (role
    -0.07
    ുന്നു
    -0.07
    家具
    -0.07
     కలిసి
    -0.07
    POSITIVE LOGITS
     ith
    0.09
     revoir
    0.08
     вывести
    0.08
     provoquer
    0.08
     coi
    0.08
     acar
    0.08
     вывод
    0.08
     sedikit
    0.08
     ауд
    0.08
     उल
    0.08
    Activations Density 0.000%

    No Known Activations