© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47921
    Prev
    Next
    INDEX
    Explanations

    machine learning datasets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     implementar
    -0.09
     biologique
    -0.08
    _NOW
    -0.08
    brevi
    -0.08
     /////
    -0.08
    _WH
    -0.07
     biologische
    -0.07
    -0.07
    ellant
    -0.07
    _SCRIPT
    -0.07
    POSITIVE LOGITS
     labelled
    0.10
     labeled
    0.09
     plentiful
    0.09
     training
    0.09
     annotated
    0.09
     histories
    0.08
     tuples
    0.08
     corpus
    0.08
     опы
    0.08
     mẫu
    0.08
    Activations Density 0.020%
    No Known Activations