Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 282
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    IDE
    -0.08
    าคาร
    -0.08
     Martín
    -0.08
     seasoned
    -0.07
     fühlt
    -0.07
    wọn
    -0.07
     Monter
    -0.07
    جة
    -0.07
     ઉપ
    -0.07
    будь
    -0.07
    POSITIVE LOGITS
     ஆகிய
    0.10
    win
    0.09
     mosaic
    0.08
     ਵਰ
    0.08
     Resist
    0.08
    /DC
    0.08
     ਗ
    0.08
    ਣਾ
    0.08
     DPS
    0.07
     ਜੋ
    0.07
    Activations Density 0.286%

    No Known Activations