© 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. 19-RESID-POST-AA
    11. 18112
    Prev
    Next
    INDEX
    Explanations

    ###

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     these
    -0.10
     Struktur
    -0.08
    these
    -0.08
    这些
    -0.08
    结构
    -0.08
    äften
    -0.08
     cấu
    -0.08
     structures
    -0.08
     estruct
    -0.07
     Estos
    -0.07
    POSITIVE LOGITS
    Usage
    0.26
     usage
    0.26
     Usage
    0.25
    _usage
    0.22
    usage
    0.21
     kullanım
    0.21
    _USAGE
    0.19
     istifad
    0.17
    Uso
    0.17
     использование
    0.17
    Activations Density 0.011%

    No Known Activations