© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108391
    Prev
    Next
    INDEX
    Explanations

    Mulholland Drive or errors

    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
    Chem
    -0.09
    '↵
    -0.08
    'class
    -0.08
     hier
    -0.08
    (attributes
    -0.07
     invasive
    -0.07
    ashtra
    -0.07
     dass
    -0.07
    ']↵
    -0.07
    -0.07
    POSITIVE LOGITS
     Jeremy
    0.08
     Leta
    0.08
     atender
    0.08
     totalt
    0.08
     enfim
    0.08
     calific
    0.08
     Larry
    0.08
     exemplary
    0.08
     مث
    0.08
     Tina
    0.07
    Activations Density 0.000%
    No Known Activations