© 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. 22871
    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
    Negative Logits
     Nivel
    -0.08
    ailer
    -0.08
     repente
    -0.08
     extremos
    -0.08
     Recuper
    -0.07
     Risk
    -0.07
    erce
    -0.07
     slider
    -0.07
    forget
    -0.07
    Medic
    -0.07
    POSITIVE LOGITS
     imprint
    0.19
     footprints
    0.16
     footprint
    0.15
     fingerprints
    0.15
     mark
    0.15
     dấu
    0.15
     lasting
    0.15
     marks
    0.14
     impact
    0.14
    印
    0.13
    Activations Density 0.008%

    No Known Activations