© 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. 103615
    Prev
    Next
    INDEX
    Explanations

    say "s" word

    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
    ਦੇ
    -0.08
    	the
    -0.08
    such
    -0.08
    ၏
    -0.08
    თან
    -0.08
    ുമായ
    -0.08
    ÷
    -0.08
    يته
    -0.08
    masına
    -0.08
    ”;
    -0.08
    POSITIVE LOGITS
     is
    0.11
    ,
    0.09
     wordt
    0.09
     blir
    0.08
     I
    0.08
     D
    0.08
    ,↵↵
    0.08
     teda
    0.08
     =
    0.08
     Hat
    0.08
    Activations Density 0.084%

    No Known Activations