© 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 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. 69687
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and code

    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
     Ctrl
    -0.09
     monos
    -0.09
     Treasure
    -0.09
     mime
    -0.08
    Ctrl
    -0.08
    Manager
    -0.08
    Serializable
    -0.08
     nood
    -0.08
     keyboards
    -0.08
     searchable
    -0.08
    POSITIVE LOGITS
     вычис
    0.15
     계산
    0.15
     computes
    0.13
    计算
    0.13
     Computes
    0.13
     गण
    0.13
     formulas
    0.13
     सूत्र
    0.12
     calcular
    0.12
     calculates
    0.12
    Activations Density 0.026%

    No Known Activations