© 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. 18189
    Prev
    Next
    INDEX
    Explanations

    iji

    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
     говорится
    -0.08
     as
    -0.08
     such
    -0.08
     mentions
    -0.08
     mentioning
    -0.07
     although
    -0.07
     astfel
    -0.07
     literally
    -0.07
     whereas
    -0.07
     though
    -0.07
    POSITIVE LOGITS
    202
    0.11
    ್ಞಾನ
    0.11
     その他
    0.11
    ్ఞ
    0.11
     新宝
    0.11
    ২০২
    0.11
    ્ઞાન
    0.11
    ២០២
    0.11
    _色
    0.11
    その他
    0.11
    Activations Density 0.003%

    No Known Activations