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. 55889
    Prev
    Next
    INDEX
    Explanations

    Offers, provisions, or presentations

    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
     लेकर
    -0.08
    го
    -0.08
     הקר
    -0.08
     plac
    -0.08
     varying
    -0.07
     Fernandez
    -0.07
     varied
    -0.07
    _IOCTL
    -0.07
    /th
    -0.07
     Gary
    -0.07
    POSITIVE LOGITS
    stash
    0.08
    xmin
    0.08
     asker
    0.08
    pink
    0.08
     kleur
    0.08
    mods
    0.08
    mst
    0.07
    ించే
    0.07
    색
    0.07
     kulay
    0.07
    Activations Density 0.451%

    No Known Activations