© 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. 22772
    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
    �
    -0.08
    mızı
    -0.08
    εύ
    -0.08
    hæ
    -0.08
    сылка
    -0.08
    params
    -0.07
    gevoegd
    -0.07
     betaal
    -0.07
    taus
    -0.07
     վերադարձ
    -0.07
    POSITIVE LOGITS
     theory
    0.20
     Theory
    0.18
    Theory
    0.16
     théorie
    0.15
     theorie
    0.15
     teoría
    0.14
     THEORY
    0.14
     Theorie
    0.13
    /stat
    0.13
     teoria
    0.12
    Activations Density 0.010%

    No Known Activations