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. 11-RESID-POST-AA
    6. 55976
    Prev
    Next
    INDEX
    Explanations

    hopes

    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
     indispensable
    -0.09
     railway
    -0.09
     splendid
    -0.09
    ①
    -0.08
    Regexp
    -0.08
     useless
    -0.08
     hardly
    -0.08
     ન
    -0.08
     தமிழ
    -0.08
     മലയാള
    -0.07
    POSITIVE LOGITS
     preventative
    0.11
     arent
    0.10
     matchup
    0.10
     isnt
    0.10
     Hernandez
    0.10
     opper
    0.09
     Graves
    0.09
     cupc
    0.09
     seperate
    0.09
    .populate
    0.09
    Activations Density 2.098%

    No Known Activations