© 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. 20263
    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
    éhension
    -0.08
     qayb
    -0.07
    分析
    -0.07
     imagin
    -0.07
     partenaire
    -0.07
     partners
    -0.07
     Analyse
    -0.07
    ’analyse
    -0.07
     verbunden
    -0.07
     imaginative
    -0.07
    POSITIVE LOGITS
     overriding
    0.42
     overrides
    0.42
     override
    0.41
     overwrite
    0.40
    Override
    0.38
     Overrides
    0.37
    override
    0.36
     Override
    0.36
    _override
    0.36
     overridden
    0.36
    Activations Density 0.048%

    No Known Activations