© 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. 15-RESID-POST-AA
    11. 16369
    Prev
    Next
    INDEX
    Explanations

    Breathing exercises involving numbers

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amment
    -0.08
    uppe
    -0.08
    Enum
    -0.08
    anguly
    -0.08
    nee
    -0.07
    anged
    -0.07
    angement
    -0.07
    allow
    -0.07
    akas
    -0.07
    но
    -0.07
    POSITIVE LOGITS
     انته
    0.09
     enlarg
    0.09
     ಹೆಚ್ಚು
    0.08
     larger
    0.08
     ทำ
    0.08
     disproportion
    0.08
     saldo
    0.08
     रिप
    0.08
     ठूलो
    0.08
     늘
    0.08
    Activations Density 0.001%

    No Known Activations