© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78465
    Prev
    Next
    INDEX
    Explanations

    &

    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
     السود
    -0.09
    UTF
    -0.08
     числе
    -0.08
     afgest
    -0.08
    ocratic
    -0.07
     Schwarz
    -0.07
    toe
    -0.07
     некоторых
    -0.07
    सर
    -0.07
    isecond
    -0.07
    POSITIVE LOGITS
    enshi
    0.08
    ']['
    0.08
    פחה
    0.08
     বিজ্ঞান
    0.08
     Diva
    0.07
    {'
    0.07
     produt
    0.07
     Vineyard
    0.07
    phe
    0.07
     especiais
    0.07
    Activations Density 0.042%

    No Known Activations