© 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. 54865
    Prev
    Next
    INDEX
    Explanations

    greater

    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
    시간
    -0.09
    ক্ষেপ
    -0.08
    ER
    -0.08
     ESA
    -0.08
    (Change
    -0.08
     Bamb
    -0.08
    렵
    -0.08
     complexion
    -0.08
     unrest
    -0.08
     divulgação
    -0.08
    POSITIVE LOGITS
     tiers
    0.10
     स्तर
    0.10
    tiers
    0.09
     tier
    0.09
    排行榜
    0.08
    )?↵
    0.08
    Tier
    0.08
     ranking
    0.08
     alebo
    0.08
    等级
    0.08
    Activations Density 0.004%

    No Known Activations