© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 103573
    Prev
    Next
    INDEX
    Explanations

    which

    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
     ինչ
    -0.11
     որն
    -0.11
     რომელსაც
    -0.11
     որոնք
    -0.11
     როგორიც
    -0.11
     რომლებ
    -0.11
     ինչը
    -0.11
     ով
    -0.11
     ինչպես
    -0.11
    怎么领
    -0.10
    POSITIVE LOGITS
     are
    0.15
    ,
    0.12
     is
    0.12
     its
    0.12
     the
    0.11
     may
    0.11
     each
    0.11
    's
    0.10
    :↵↵
    0.10
     lies
    0.10
    Activations Density 0.010%

    No Known Activations