© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111344
    Prev
    Next
    INDEX
    Explanations

    crafting recipes

    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
     taxes
    -0.08
     Bulgar
    -0.08
     Taxes
    -0.08
     pente
    -0.07
     capacity
    -0.07
     sufficiently
    -0.07
     Armenian
    -0.07
     Delhi
    -0.07
     STATE
    -0.07
     authority
    -0.07
    POSITIVE LOGITS
    ancode
    0.09
    Pattern
    0.09
     patrones
    0.09
     Pattern
    0.09
     brauch
    0.09
     ദിന
    0.08
     рабочих
    0.08
    .Day
    0.08
     ദിവസ
    0.08
    .Tool
    0.08
    Activations Density 0.004%

    No Known Activations