© 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. 21067
    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
    Kho
    -0.08
     stochastic
    -0.07
    rxjs
    -0.07
    Text
    -0.07
    ഖ
    -0.07
    igo
    -0.07
    Corpus
    -0.07
    （月
    -0.07
     adhesives
    -0.07
     تحقیقات
    -0.07
    POSITIVE LOGITS
     servir
    0.33
     serving
    0.32
     served
    0.31
     serve
    0.31
     servido
    0.31
     Serve
    0.30
     Served
    0.30
     Serving
    0.30
     sirven
    0.29
    Serving
    0.29
    Activations Density 0.089%

    No Known Activations