© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19539
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     excavation
    -0.11
    新华社
    -0.09
    Scatter
    -0.09
     eyewitness
    -0.09
     Hiroshima
    -0.09
    (robot
    -0.09
     Excav
    -0.09
     pedestrians
    -0.09
     bfs
    -0.09
    Terrain
    -0.09
    POSITIVE LOGITS
     subscription
    0.28
     Subscription
    0.27
    Subscription
    0.27
    _subscription
    0.27
    .subscription
    0.26
     billing
    0.26
    subscription
    0.26
     subscriptions
    0.25
     abonnement
    0.25
    .Subscription
    0.25
    Activations Density 0.038%

    No Known Activations