© 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. 63500
    Prev
    Next
    INDEX
    Explanations

    for

    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
     évo
    -0.09
     lei
    -0.08
     juntar
    -0.08
    वर्क
    -0.07
    ความ
    -0.07
     mound
    -0.07
    ologue
    -0.07
     grinder
    -0.07
     electoral
    -0.07
     आवश्यकता
    -0.07
    POSITIVE LOGITS
     সকল
    0.09
     అన్ని
    0.09
     সমস্ত
    0.09
     every
    0.09
     બધા
    0.09
     તમામ
    0.08
     tất
    0.08
     ANY
    0.08
    多年
    0.08
     Leb
    0.08
    Activations Density 0.028%

    No Known Activations