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. 55864
    Prev
    Next
    INDEX
    Explanations

    additive

    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
     bahkan
    -0.08
    .design
    -0.08
     Attorney
    -0.07
     Hey
    -0.07
     Healthcare
    -0.07
     Ugly
    -0.07
     tulisan
    -0.07
     美
    -0.07
    bias
    -0.07
     페이지
    -0.07
    POSITIVE LOGITS
    ими
    0.08
     lựa
    0.08
     speech
    0.08
    ിം
    0.08
     выбора
    0.08
     Swarovski
    0.08
    選
    0.08
     الأش
    0.07
    ಿಸಲ
    0.07
     выборе
    0.07
    Activations Density 0.001%

    No Known Activations