© 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. 11-RESID-POST-AA
    11. 71480
    Prev
    Next
    INDEX
    Explanations

    to

    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
    came
    -0.09
     eem
    -0.08
    angar
    -0.08
    entai
    -0.08
     memes
    -0.08
    াধ
    -0.08
    cult
    -0.08
    进行了
    -0.08
     করেছি
    -0.07
     mma
    -0.07
    POSITIVE LOGITS
     unsuccessful
    0.09
    Reasons
    0.08
    失败
    0.08
     실패
    0.08
     failures
    0.08
     failure
    0.08
     heutzutage
    0.08
     roku
    0.08
    гора
    0.08
     vieler
    0.07
    Activations Density 0.089%

    No Known Activations