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. 15-RESID-POST-AA
    6. 19132
    Prev
    Next
    INDEX
    Explanations

    sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beyond
    -0.08
    stdint
    -0.08
     Five
    -0.08
     Ign
    -0.07
     Thorough
    -0.07
     Pessoa
    -0.07
    .length
    -0.07
     Physical
    -0.07
     hrs
    -0.07
     IPO
    -0.07
    POSITIVE LOGITS
     negative
    0.09
     negat
    0.09
    ?↵↵
    0.08
     отриц
    0.08
     tegenover
    0.08
     adjustments
    0.08
     adjustment
    0.08
     correctly
    0.08
     negatif
    0.08
     negativity
    0.08
    Activations Density 0.012%

    No Known Activations