© 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. 102261
    Prev
    Next
    INDEX
    Explanations

    Use/utilize in other languages

    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
     usare
    -0.10
     gamitin
    -0.09
     используют
    -0.09
     use
    -0.09
     använda
    -0.09
     bruke
    -0.08
     använder
    -0.08
     nutzt
    -0.08
    use
    -0.08
     utilisent
    -0.08
    POSITIVE LOGITS
    하여
    0.19
     કરીને
    0.18
     отырып
    0.17
    ിച്ച്
    0.17
    ၍
    0.17
     करून
    0.16
    ಿಕೊಂಡ
    0.16
    ऊन
    0.16
     गरेर
    0.16
    ుకుని
    0.16
    Activations Density 0.003%

    No Known Activations