© 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. 648
    Prev
    Next
    INDEX
    Explanations

    内容

    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
     revived
    -0.08
    Feign
    -0.07
    Vy
    -0.07
     revive
    -0.07
    Nick
    -0.07
    SID
    -0.07
    感染
    -0.07
     graphi
    -0.07
    SAT
    -0.07
     বে
    -0.07
    POSITIVE LOGITS
     пунк
    0.09
    ale
    0.08
    brevi
    0.08
     Essay
    0.08
    try
    0.08
     numbered
    0.08
     rhin
    0.08
    pod
    0.08
     commandments
    0.07
    ️
    0.07
    Activations Density 0.003%

    No Known Activations