© 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. 17915
    Prev
    Next
    INDEX
    Explanations

    forward slash

    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
     missing
    -0.10
     then
    -0.08
     Missing
    -0.08
    Missing
    -0.07
     modules
    -0.07
     as
    -0.07
    ousand
    -0.07
     unik
    -0.07
     mellitus
    -0.07
     supposed
    -0.07
    POSITIVE LOGITS
    /music
    0.09
    Places
    0.08
    日下午
    0.08
    _spaces
    0.08
     Calls
    0.08
    ထား
    0.08
    .Cloud
    0.08
    ��
    0.08
    _reads
    0.08
     ouverte
    0.08
    Activations Density 0.001%

    No Known Activations