© 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. 11-RESID-POST-AA
    11. 7798
    Prev
    Next
    INDEX
    Explanations

    Mathematical segments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Weih
    -0.08
     sej
    -0.08
     שע
    -0.08
     iwi
    -0.08
     and
    -0.07
    751
    -0.07
     Domen
    -0.07
    629
    -0.07
     Luxus
    -0.07
     allerede
    -0.07
    POSITIVE LOGITS
    比如
    0.09
     مانند
    0.09
     όπως
    0.09
    ，比如
    0.09
     যেমন
    0.09
    ＝
    0.08
    como
    0.08
    例えば
    0.08
    sten
    0.08
     zoals
    0.08
    Activations Density 0.210%

    No Known Activations