© 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 EvalsExportsAPI 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. 21031
    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
     taget
    -0.08
    าชิก
    -0.08
     аса
    -0.08
     hesitate
    -0.08
    ousing
    -0.08
     fark
    -0.08
     hés
    -0.08
    -0.07
     perkara
    -0.07
     נע
    -0.07
    POSITIVE LOGITS
     explains
    0.34
     explain
    0.34
     explaining
    0.33
    解释
    0.33
     объяс
    0.32
    説明
    0.31
     explicar
    0.31
     explica
    0.31
     설명
    0.30
     expliquer
    0.30
    Activations Density 0.042%
    No Known Activations