© 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. 44602
    Prev
    Next
    INDEX
    Explanations

    the

    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
     CEOs
    -0.09
     Rebels
    -0.09
     allies
    -0.08
     amici
    -0.08
     nurses
    -0.08
     Prospect
    -0.08
     chiefs
    -0.08
     Chiefs
    -0.08
     Galleries
    -0.08
     Wag
    -0.08
    POSITIVE LOGITS
     слово
    0.09
     слова
    0.09
     حرف
    0.08
    sé
    0.08
     letter
    0.08
     букв
    0.08
     لفظ
    0.07
    (E
    0.07
     usages
    0.07
    sí
    0.07
    Activations Density 0.004%

    No Known Activations