© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 71762
    Prev
    Next
    INDEX
    Explanations

    excludes value zero

    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
    Negative Logits
     हुई
    -0.09
     MAD
    -0.08
    ಟ್ಟು
    -0.08
     piso
    -0.08
     Μ
    -0.08
     unidade
    -0.08
     निर्ण
    -0.07
    ّت
    -0.07
    ाऱ्या
    -0.07
    ہم
    -0.07
    POSITIVE LOGITS
    `()
    0.08
     exercising
    0.08
     sombr
    0.07
     carries
    0.07
    Activity
    0.07
    ).__
    0.07
     Exercise
    0.07
    utorial
    0.07
     itse
    0.07
     cultured
    0.07
    Activations Density 0.049%

    No Known Activations