© 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. 65014
    Prev
    Next
    INDEX
    Explanations

    answering questions

    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
     advocate
    -0.08
     cael
    -0.08
    ieniem
    -0.08
    ssen
    -0.08
     ''}↵
    -0.08
     boost
    -0.08
     advocating
    -0.07
    izzly
    -0.07
     əldə
    -0.07
    Taylor
    -0.07
    POSITIVE LOGITS
     weakness
    0.11
     weaknesses
    0.10
    哪个
    0.10
     कमजोर
    0.10
     faulty
    0.10
     Wrong
    0.10
     कमज
    0.10
    (selected
    0.10
     rashin
    0.09
     offending
    0.09
    Activations Density 0.033%

    No Known Activations