© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6339
    Prev
    Next
    INDEX
    Explanations

    of

    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
    argo
    -0.08
     dễ
    -0.08
     wc
    -0.08
     carrot
    -0.08
     plantas
    -0.08
    pụta
    -0.07
     tastes
    -0.07
     altres
    -0.07
     fecha
    -0.07
     Takes
    -0.07
    POSITIVE LOGITS
     Consulting
    0.09
     consulting
    0.09
     Environmental
    0.09
    Environmental
    0.09
     nervous
    0.08
    宁县
    0.08
     abnormal
    0.08
     environmental
    0.08
     affect
    0.08
     참
    0.08
    Activations Density 0.001%

    No Known Activations