© 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. 44909
    Prev
    Next
    INDEX
    Explanations

    physical objects

    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
     kanjani
    -0.09
     capitalization
    -0.09
     thì
    -0.08
    께
    -0.08
    ctx
    -0.08
     sabemos
    -0.08
    }}↵↵
    -0.07
    !"↵↵
    -0.07
    !)↵↵
    -0.07
     ctx
    -0.07
    POSITIVE LOGITS
    不断
    0.09
    ，由
    0.08
     специальные
    0.08
     resembling
    0.08
     ув
    0.08
    ，被
    0.08
     namens
    0.08
     هون
    0.08
     comprising
    0.07
     agradável
    0.07
    Activations Density 0.124%

    No Known Activations