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. 12961
    Prev
    Next
    INDEX
    Explanations

    Business

    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
     Hundred
    -0.08
     JDBC
    -0.08
    omach
    -0.08
    Jdbc
    -0.08
    lacht
    -0.08
    wissenschaft
    -0.07
    -0.07
    ږي
    -0.07
     JCombo
    -0.07
     gw
    -0.07
    POSITIVE LOGITS
    ACE
    0.08
    ván
    0.08
     ACE
    0.07
     Agree
    0.07
    ACES
    0.07
    Agree
    0.07
     thrive
    0.07
     таких
    0.07
     ub
    0.07
    革
    0.07
    Activations Density 0.001%

    No Known Activations