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. 12211
    Prev
    Next
    INDEX
    Explanations

    Cooking spices

    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
    iaux
    -0.08
    ైవ
    -0.08
     antibody
    -0.08
     אית
    -0.08
    ávamos
    -0.08
     incó
    -0.08
     jeopard
    -0.08
     sai
    -0.08
    (parcel
    -0.07
     साबित
    -0.07
    POSITIVE LOGITS
    �
    0.08
     tone
    0.07
    HI
    0.07
     dekor
    0.07
     versehen
    0.07
    ంద
    0.07
     Morocco
    0.07
     szere
    0.07
     poudre
    0.07
     seleccion
    0.07
    Activations Density 0.002%

    No Known Activations