© 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. 17910
    Prev
    Next
    INDEX
    Explanations

    了

    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
     anuncio
    -0.08
    yndan
    -0.08
     ועד
    -0.08
    ottie
    -0.08
    ritter
    -0.08
    ummy
    -0.07
    ANNOT
    -0.07
     zabez
    -0.07
     persoane
    -0.07
     lieve
    -0.07
    POSITIVE LOGITS
     दिशा
    0.20
     direction
    0.20
     방향
    0.20
    方向
    0.20
     Richtung
    0.18
    Direction
    0.18
     Direction
    0.18
    _direction
    0.17
     direção
    0.17
     направление
    0.17
    Activations Density 0.011%

    No Known Activations