© 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. 30430
    Prev
    Next
    INDEX
    Explanations

    3

    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
    투
    -0.08
     आपकी
    -0.08
    abbat
    -0.08
    Circular
    -0.07
     Minneapolis
    -0.07
    enswert
    -0.07
     predicted
    -0.07
     circular
    -0.07
     투
    -0.07
     구축
    -0.07
    POSITIVE LOGITS
    лиги
    0.09
    _lista
    0.09
    Lista
    0.08
     lic
    0.08
     число
    0.08
     Moyen
    0.08
    .floor
    0.08
    лиг
    0.08
     Liga
    0.08
    .basename
    0.08
    Activations Density 0.063%

    No Known Activations