© 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. 44846
    Prev
    Next
    INDEX
    Explanations

    New Delhi news

    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
    牛牛
    -0.08
    νες
    -0.08
    dür
    -0.08
    tensorflow
    -0.08
    .stere
    -0.08
    �
    -0.08
    avorite
    -0.08
    ्दा
    -0.07
     пользоваться
    -0.07
     ī
    -0.07
    POSITIVE LOGITS
    _CITY
    0.08
    600
    0.08
    agena
    0.07
     hvor
    0.07
     기자
    0.07
     ruang
    0.07
    News
    0.07
    0.07
     lignes
    0.07
    JO
    0.07
    Activations Density 0.066%
    No Known Activations