© 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. 108623
    Prev
    Next
    INDEX
    Explanations

    root

    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
    iegt
    -0.08
     rot
    -0.08
     plight
    -0.08
    tok
    -0.07
    tom
    -0.07
    ching
    -0.07
    țiile
    -0.07
     Bonn
    -0.07
    rot
    -0.07
    zg
    -0.07
    POSITIVE LOGITS
    most
    0.11
    -most
    0.10
    तः
    0.10
    -level
    0.09
    级
    0.09
    /root
    0.09
    สุด
    0.09
     asti
    0.09
    とな
    0.09
    ‌ترین
    0.08
    Activations Density 0.007%

    No Known Activations