© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18224
    Prev
    Next
    INDEX
    Explanations

    Counting items

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gedrag
    -0.09
    ♀♀
    -0.09
    합뉴스
    -0.08
    anjem
    -0.08
    ารี
    -0.08
    осква
    -0.08
    দন্ত
    -0.08
    还是假的
    -0.08
     behavi
    -0.08
    计划软件
    -0.08
    POSITIVE LOGITS
     individually
    0.13
    's
    0.13
     posebej
    0.13
     afzonder
    0.12
    都
    0.12
    都是
    0.11
     separately
    0.10
     hinweg
    0.10
    都有
    0.10
    的
    0.09
    Activations Density 0.060%

    No Known Activations