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. 58619
    Prev
    Next
    INDEX
    Explanations

    Repulsion between charges

    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
    Frames
    -0.09
    ABOUT
    -0.08
     ABOUT
    -0.08
     Intervention
    -0.08
    Frame
    -0.08
     Frames
    -0.08
    LT
    -0.08
     bookstore
    -0.08
    Tls
    -0.08
    Inactive
    -0.08
    POSITIVE LOGITS
     adjacent
    0.08
     repel
    0.07
    料金
    0.07
     birbir
    0.07
     �
    0.07
     međ
    0.07
    atern
    0.07
    utting
    0.07
     afval
    0.07
     sable
    0.07
    Activations Density 0.004%

    No Known Activations