© 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. 77925
    Prev
    Next
    INDEX
    Explanations

    oti

    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
     المزيد
    -0.09
    
    -0.09
     mooie
    -0.07
     красив
    -0.07
    ijah
    -0.07
     alternate
    -0.07
    로
    -0.07
    rowave
    -0.07
    ogle
    -0.07
     alternating
    -0.07
    POSITIVE LOGITS
     మాత్రం
    0.10
     Mindest
    0.09
     unacceptable
    0.09
     mindig
    0.09
     grundleg
    0.09
     vždy
    0.09
     Integrity
    0.09
     tamen
    0.09
     fundamentally
    0.09
     mínimos
    0.09
    Activations Density 0.056%

    No Known Activations