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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103001
    Prev
    Next
    INDEX
    Explanations

    or

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -0.09
     via
    -0.09
    .
    -0.09
     DIFFER
    -0.08
     as
    -0.08
     but
    -0.08
     različnih
    -0.08
     色
    -0.08
     with
    -0.08
    _filtered
    -0.08
    POSITIVE LOGITS
     instructions
    0.14
     инструкции
    0.12
     инструк
    0.12
     Anleitung
    0.11
     instrucciones
    0.11
     инструкция
    0.11
     advice
    0.11
     conseils
    0.11
     consejos
    0.11
     советы
    0.11
    Activations Density 0.001%

    No Known Activations