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

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 97873
    Prev
    Next
    INDEX
    Explanations

    refining

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _disabled
    -0.08
     deactivate
    -0.08
     restarted
    -0.08
     deaktiv
    -0.08
     verkla
    -0.07
    Disabled
    -0.07
    _restart
    -0.07
    plicht
    -0.07
     acompanhar
    -0.07
     disable
    -0.07
    POSITIVE LOGITS
     refining
    0.44
     refine
    0.43
     refinement
    0.41
     fine
    0.39
     refined
    0.38
     Refin
    0.38
     refin
    0.37
    fine
    0.35
     Fine
    0.35
    Fine
    0.34
    Activations Density 0.131%

    No Known Activations