© 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 EvalsExportsinterp-engineNEWAPI 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. 18962
    Prev
    Next
    INDEX
    Explanations

    variations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    'яўляецца
    -0.09
     birçok
    -0.09
     vielen
    -0.09
     mnog
    -0.09
     många
    -0.09
     molti
    -0.09
     अधिकांश
    -0.08
     Banyak
    -0.08
     ઘણ
    -0.08
     muitos
    -0.08
    POSITIVE LOGITS
     differing
    0.17
     unterschiedlichen
    0.14
     tofauti
    0.14
     unterschiedliche
    0.14
     διαφορε
    0.14
     unterscheiden
    0.14
     مختلفة
    0.13
     differentiated
    0.13
     distinct
    0.13
     diferan
    0.13
    Activations Density 0.013%

    No Known Activations