© 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. 103399
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     třeba
    -0.08
     kanskje
    -0.08
     možda
    -0.08
     նաև
    -0.08
     misschien
    -0.08
     akár
    -0.08
     uga
    -0.07
     måske
    -0.07
     quizás
    -0.07
     এমন
    -0.07
    POSITIVE LOGITS
    。因此
    0.22
    。所以
    0.20
    .
    0.16
    .↵↵
    0.13
    ，因此
    0.13
     ולכן
    0.13
    。但是
    0.13
    。如果
    0.13
    .↵
    0.12
    ।
    0.12
    Activations Density 0.074%

    No Known Activations