© 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. 19991
    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
     tecnica
    -0.08
    ��
    -0.08
    maker
    -0.07
    author
    -0.07
    ream
    -0.07
    itudes
    -0.07
     praised
    -0.07
    /or
    -0.07
     البشرية
    -0.07
     costly
    -0.07
    POSITIVE LOGITS
    ization
    0.15
    ized
    0.13
    izable
    0.13
    isation
    0.13
    ización
    0.12
    izacion
    0.12
    转载请
    0.11
    IZATION
    0.11
    izasyon
    0.11
    izing
    0.11
    Activations Density 0.011%

    No Known Activations