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. 76480
    Prev
    Next
    INDEX
    Explanations

    business/credit

    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
    tten
    -0.08
    چه
    -0.08
    씩
    -0.08
     инстру
    -0.08
     embassy
    -0.07
    	volatile
    -0.07
    quilla
    -0.07
    -appointed
    -0.07
    Victor
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     illusions
    0.08
    ,以及
    0.08
     Wey
    0.08
    ™
    0.07
    ίου
    0.07
    0.07
    ক্রান্ত
    0.07
    iety
    0.07
     fark
    0.07
    otle
    0.07
    Activations Density 2.878%

    No Known Activations