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. 53278
    Prev
    Next
    INDEX
    Explanations

    questions asked

    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
    Brown
    -0.09
     densely
    -0.09
    NFT
    -0.08
    изи
    -0.08
    Ron
    -0.08
    Common
    -0.08
    mino
    -0.08
    izacion
    -0.08
    NAV
    -0.08
     ornamental
    -0.08
    POSITIVE LOGITS
     Backup
    0.09
     Fragen
    0.09
     Questions
    0.08
     Kriterien
    0.08
     Comparison
    0.08
    gült
    0.08
     Comparing
    0.08
     Opposition
    0.08
     Matching
    0.08
     Verification
    0.08
    Activations Density 0.010%

    No Known Activations