© 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. 68380
    Prev
    Next
    INDEX
    Explanations

    balanced

    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
     passport
    -0.08
     SORT
    -0.07
     verfügbar
    -0.07
     Tas
    -0.07
     grate
    -0.07
     Delf
    -0.07
     Madr
    -0.07
    -п
    -0.07
     Vat
    -0.07
    .wik
    -0.07
    POSITIVE LOGITS
    balance
    0.15
     balance
    0.14
    Balance
    0.14
     équilibr
    0.14
     équilibre
    0.13
     equilibrio
    0.13
    _balance
    0.13
     Balance
    0.13
     balancing
    0.13
     equilíbrio
    0.13
    Activations Density 0.004%

    No Known Activations