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. 56214
    Prev
    Next
    INDEX
    Explanations

    Game of Thrones

    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
    -component
    -0.08
    -aos
    -0.07
     artística
    -0.07
     Rost
    -0.07
     торм
    -0.07
     Shiva
    -0.07
     primit
    -0.07
    arshal
    -0.07
    _SHADER
    -0.07
    -stage
    -0.07
    POSITIVE LOGITS
     coveted
    0.09
     الجزيرة
    0.09
    দান
    0.08
     claimed
    0.08
    BOTTOM
    0.08
     proposées
    0.08
     جنيه
    0.08
     proposent
    0.08
    锅
    0.08
     UNITED
    0.08
    Activations Density 0.004%

    No Known Activations