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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70565
    Prev
    Next
    INDEX
    Explanations

    hits

    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
    ']}
    -0.08
    -house
    -0.08
    ']}↵
    -0.08
     casque
    -0.07
     등에
    -0.07
    }`}>↵
    -0.07
     ''}↵
    -0.07
     เป็นต้น
    -0.07
     headphones
    -0.07
    ด้าน
    -0.07
    POSITIVE LOGITS
     ఎవ
    0.08
    秀
    0.08
    総
    0.08
    综合
    0.08
    indwa
    0.07
     કુલ
    0.07
     exchanged
    0.07
     సో
    0.07
    患者
    0.07
    净
    0.07
    Activations Density 0.010%

    No Known Activations