© 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. 31240
    Prev
    Next
    INDEX
    Explanations

    blood pressure reduction

    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
     BOOL
    -0.08
     وار
    -0.08
     عباد
    -0.07
    繁
    -0.07
     Outs
    -0.07
    .edu
    -0.07
     fars
    -0.07
    ിര
    -0.07
     siyang
    -0.07
    .pro
    -0.07
    POSITIVE LOGITS
     fasting
    0.09
    ∆
    0.09
    [F
    0.09
    Δ
    0.09
     promedio
    0.09
     Bland
    0.09
     gemiddeld
    0.08
     grub
    0.08
     statistically
    0.08
    Delta
    0.08
    Activations Density 0.011%

    No Known Activations