© 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. 44817
    Prev
    Next
    INDEX
    Explanations

    Chinese characters/radicals

    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
     резерв
    -0.09
     contrasts
    -0.08
     Bonds
    -0.08
     resonance
    -0.07
    ];↵↵↵
    -0.07
    brief
    -0.07
     resonate
    -0.07
     stabilize
    -0.07
    inig
    -0.07
    .";↵↵
    -0.07
    POSITIVE LOGITS
    وات
    0.08
     radicals
    0.08
     watery
    0.07
     depicting
    0.07
    icating
    0.07
    �
    0.07
     إذ
    0.07
     آهن
    0.07
    ***/
    0.07
     هزینه
    0.07
    Activations Density 0.003%

    No Known Activations