© 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. 25933
    Prev
    Next
    INDEX
    Explanations

    Kalman filter

    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
     vegetarian
    -0.10
     toppings
    -0.09
     emoji
    -0.09
     slogan
    -0.09
     roasting
    -0.09
     chocolate
    -0.09
     emojis
    -0.08
     seasoning
    -0.08
     delighted
    -0.08
     đảo
    -0.08
    POSITIVE LOGITS
     Kal
    0.15
    Kal
    0.13
     kal
    0.12
     estime
    0.11
    estimate
    0.11
    Estimate
    0.11
    估
    0.11
     estimates
    0.10
     Кал
    0.10
    Gaussian
    0.10
    Activations Density 0.006%

    No Known Activations