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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 94421
    Prev
    Next
    INDEX
    Explanations

    Code and math symbols

    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
     Several
    -0.08
     plusieurs
    -0.08
     जाग
    -0.07
    、中
    -0.07
    ,:,
    -0.07
    очка
    -0.07
    ווח
    -0.07
    ट
    -0.07
    alia
    -0.07
    फ़
    -0.07
    POSITIVE LOGITS
     letzt
    0.09
     lastly
    0.09
    —all
    0.09
     schließlich
    0.08
     ellos
    0.08
     смер
    0.08
    勒比
    0.08
    yii
    0.08
    yram
    0.08
    都有
    0.08
    Activations Density 0.125%

    No Known Activations