© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 18088
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives

    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
     müsste
    -0.09
     ಕೆಲವು
    -0.08
     nějak
    -0.08
     moesten
    -0.08
     некотор
    -0.08
     devront
    -0.08
     трябва
    -0.08
     προσπά
    -0.08
     некоторые
    -0.08
     some
    -0.08
    POSITIVE LOGITS
     bessere
    0.14
     besseren
    0.14
     richer
    0.13
     гораздо
    0.13
     बेहतर
    0.13
     betere
    0.13
     легче
    0.12
     stronger
    0.12
     migliori
    0.12
     healthier
    0.12
    Activations Density 0.127%

    No Known Activations