© 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. 17935
    Prev
    Next
    INDEX
    Explanations

    equations

    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
    Negative Logits
    -kar
    -0.08
    -remove
    -0.08
    撤
    -0.08
    -日本
    -0.08
    一个
    -0.08
     Cerr
    -0.07
    -sort
    -0.07
     મુખ્ય
    -0.07
    -K
    -0.07
    -toast
    -0.07
    POSITIVE LOGITS
     equations
    0.08
    ategy
    0.08
    _attempt
    0.08
     effetti
    0.08
     achieving
    0.08
    Congrats
    0.08
     youngest
    0.08
     ==↵
    0.08
    _possible
    0.08
    ()}
    0.07
    Activations Density 0.000%

    No Known Activations