© 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. 95636
    Prev
    Next
    INDEX
    Explanations

    About, approximately

    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
     spullen
    -0.09
    tia
    -0.08
     aquilo
    -0.08
     relazione
    -0.08
     dingen
    -0.08
     jotain
    -0.08
     Things
    -0.08
     şey
    -0.07
     stap
    -0.07
     funniest
    -0.07
    POSITIVE LOGITS
     herein
    0.10
     করছি
    0.09
     hereby
    0.08
    :</
    0.08
    ಿಸಲಾಗಿದೆ
    0.08
    .";↵↵
    0.08
    :\\
    0.08
     omitted
    0.08
     hieronder
    0.08
     ordinarily
    0.08
    Activations Density 0.128%

    No Known Activations