© 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. 23-RESID-POST-AA
    11. 52079
    Prev
    Next
    INDEX
    Explanations

    automated systems

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     જ્યારે
    -0.11
    	when
    -0.10
     যখন
    -0.09
     Whenever
    -0.09
     everytime
    -0.09
     when
    -0.09
    when
    -0.09
     acompanhar
    -0.09
    .when
    -0.09
     když
    -0.09
    POSITIVE LOGITS
     trigger
    0.18
     triggers
    0.17
     triggering
    0.17
    Trigger
    0.17
    trigger
    0.17
     Trigger
    0.17
    _trigger
    0.16
     activates
    0.16
     activar
    0.16
    触
    0.16
    Activations Density 0.052%

    No Known Activations