© 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. 68144
    Prev
    Next
    INDEX
    Explanations

    render

    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
    🏼
    -0.08
    iface
    -0.07
    vali
    -0.07
     Joan
    -0.07
    🏻
    -0.07
    プレ
    -0.07
     fino
    -0.07
    _taken
    -0.07
    ırs
    -0.07
     enr
    -0.06
    POSITIVE LOGITS
     تو
    0.10
     lit
    0.09
     erzielen
    0.08
    -lit
    0.08
     spe
    0.07
     dude
    0.07
    .githubusercontent
    0.07
    .norm
    0.07
    owanie
    0.07
     Zem
    0.07
    Activations Density 0.008%

    No Known Activations