© 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. 30164
    Prev
    Next
    INDEX
    Explanations

    9

    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
     endemic
    -0.09
    ป
    -0.07
    נד
    -0.07
    פס
    -0.07
     việc
    -0.07
     Bah
    -0.07
     Pride
    -0.07
    �
    -0.07
     నిర
    -0.07
    며
    -0.07
    POSITIVE LOGITS
    adecimal
    0.09
    歳
    0.08
    nasium
    0.08
    ️⃣
    0.08
     మంది
    0.08
    lijkse
    0.08
     числа
    0.08
    755
    0.07
    号
    0.07
     সংখ্য
    0.07
    Activations Density 0.311%

    No Known Activations