© 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. 64842
    Prev
    Next
    INDEX
    Explanations

    Blood pressure/lipids levels

    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
     آدم
    -0.08
     Ég
    -0.08
     وقتی
    -0.08
     Þegar
    -0.08
    hebbers
    -0.08
     verlaten
    -0.08
     Eigen
    -0.08
    íocht
    -0.08
     Ego
    -0.08
    irical
    -0.08
    POSITIVE LOGITS
     cardiovascular
    0.08
     tighter
    0.08
     tightening
    0.08
     tightened
    0.08
    ulina
    0.08
     hypertension
    0.07
     obesity
    0.07
     scelta
    0.07
    Unified
    0.07
     fasting
    0.07
    Activations Density 0.005%

    No Known Activations