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. 111524
    Prev
    Next
    INDEX
    Explanations

    Linux GRUB configuration

    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
    matched
    -0.07
     dependencia
    -0.07
     Cup
    -0.07
    ाती
    -0.07
    Cup
    -0.07
    igi
    -0.07
     Reglamento
    -0.07
    |min
    -0.07
    кой
    -0.07
     fixtures
    -0.07
    POSITIVE LOGITS
     autism
    0.09
     tweak
    0.08
     inquiry
    0.08
     prze
    0.08
     speeding
    0.08
     tweaking
    0.08
     hind
    0.08
    orce
    0.08
     aman
    0.07
    _De
    0.07
    Activations Density 0.006%

    No Known Activations