© 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. 7-RESID-POST-AA
    11. 1031
    Prev
    Next
    INDEX
    Explanations

    being stopped by something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ausbau
    -0.09
     Skate
    -0.08
     Chiropr
    -0.08
     soigne
    -0.08
    hub
    -0.08
     intercourse
    -0.08
    .Composite
    -0.08
     réserve
    -0.08
     Й
    -0.07
     musste
    -0.07
    POSITIVE LOGITS
    ்கு
    0.08
     traditional
    0.08
     каким
    0.08
    traditional
    0.08
     mundane
    0.08
     Palma
    0.08
     merely
    0.08
    થી
    0.08
     महामारी
    0.07
     anything
    0.07
    Activations Density 0.084%

    No Known Activations