© 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. 94587
    Prev
    Next
    INDEX
    Explanations

    variables in math

    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
    ابت
    -0.08
     terr
    -0.07
     immobil
    -0.07
    قدم
    -0.07
     plating
    -0.07
     méth
    -0.07
     lance
    -0.07
     geste
    -0.07
    یزی
    -0.07
       ↵↵
    -0.07
    POSITIVE LOGITS
     парламент
    0.09
     татар
    0.08
     парла
    0.08
     уу
    0.08
    Quaternion
    0.08
     Ei
    0.08
     депутат
    0.08
     tenor
    0.08
     супруг
    0.08
    raud
    0.08
    Activations Density 0.025%

    No Known Activations