© 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. 11-RESID-POST-AA
    11. 44652
    Prev
    Next
    INDEX
    Explanations

    of

    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
    泉
    -0.09
     PCB
    -0.08
     Epson
    -0.08
     DOE
    -0.08
     estan
    -0.08
     sce
    -0.08
    (Android
    -0.08
     Android
    -0.07
     SDK
    -0.07
    ERICA
    -0.07
    POSITIVE LOGITS
    Supply
    0.09
     faction
    0.09
    _supply
    0.09
    Warnings
    0.09
     empire
    0.09
     Bravo
    0.08
     factions
    0.08
     alliances
    0.08
     horrific
    0.08
    Warning
    0.08
    Activations Density 0.012%

    No Known Activations