Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76401
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    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
     عد
    -0.08
    Raid
    -0.07
     du
    -0.07
     wildcard
    -0.07
     تنظیم
    -0.07
    仕様
    -0.07
    ?),
    -0.07
     sma
    -0.07
     ਸ਼
    -0.07
     ду
    -0.07
    POSITIVE LOGITS
     happier
    0.09
     happiest
    0.09
     brighter
    0.09
     niż
    0.09
    halten
    0.09
    ợp
    0.08
    _mutex
    0.08
    อกจากนี้
    0.08
    	mutex
    0.08
     outperform
    0.08
    Activations Density 0.063%

    No Known Activations