© 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. 11-RESID-POST-AA
    11. 47357
    Prev
    Next
    INDEX
    Explanations

    ing

    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
     humanidad
    -0.08
     avulla
    -0.08
     Laura
    -0.08
     Elsa
    -0.08
    ულის
    -0.08
     vlast
    -0.08
     उद्ध
    -0.08
     australia
    -0.08
    真实吗
    -0.08
     humanidade
    -0.08
    POSITIVE LOGITS
     nécess
    0.10
     requiring
    0.09
    requires
    0.09
     needing
    0.09
    requ
    0.09
     doeleinden
    0.09
     wanting
    0.09
    Requires
    0.08
     Zwecke
    0.08
    ต้อง
    0.08
    Activations Density 0.054%

    No Known Activations