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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 49138
    Prev
    Next
    INDEX
    Explanations

    fingerprint

    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
     Pare
    -0.09
    �
    -0.08
    .append
    -0.07
    Pare
    -0.07
     pst
    -0.07
    trajectory
    -0.07
    ช่วง
    -0.07
    trav
    -0.07
    策
    -0.07
     மு�
    -0.07
    POSITIVE LOGITS
     usability
    0.09
    Authenticate
    0.09
    Encrypted
    0.09
    Authentication
    0.09
     leitor
    0.09
    Matter
    0.09
     headphones
    0.08
     Authentication
    0.08
     authentication
    0.08
    Decrypt
    0.08
    Activations Density 0.002%

    No Known Activations