Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60773
    Prev
    Next
    INDEX
    Explanations

    Mathematical arrays

    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
     liés
    -0.08
     incontournable
    -0.07
     fulfill
    -0.07
    िवार
    -0.07
    ociation
    -0.07
    主动
    -0.07
    endeu
    -0.07
    -found
    -0.07
     indig
    -0.07
    obus
    -0.07
    POSITIVE LOGITS
    0.08
     улсын
    0.08
     фот
    0.08
     televis
    0.08
     slag
    0.08
     телефона
    0.08
    hlelo
    0.08
     Check
    0.07
     WL
    0.07
     hems
    0.07
    Activations Density 0.006%

    No Known Activations