© 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. 18166
    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
     fois
    -0.09
     any
    -0.08
     ерекше
    -0.08
     सारे
    -0.08
     time
    -0.07
     განსაკუთრ
    -0.07
    "*
    -0.07
     ndlela
    -0.07
    ्शन
    -0.07
     "
    -0.07
    POSITIVE LOGITS
    ≈
    0.13
     ongeveer
    0.12
     około
    0.12
     約
    0.11
    approximately
    0.11
    about
    0.11
    約
    0.11
     ಸುಮಾರು
    0.11
     (~
    0.11
     roughly
    0.11
    Activations Density 0.014%

    No Known Activations