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

    Neuronpedia

    Jacobian LensNEW
    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. 113274
    Prev
    Next
    INDEX
    Explanations

    Question answering snippet beginnings

    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
     inauguration
    -0.08
     Dyn
    -0.08
    Exceptional
    -0.08
     innings
    -0.08
     undefeated
    -0.08
    ordinal
    -0.08
    Contest
    -0.07
     matchup
    -0.07
     Elections
    -0.07
     valign
    -0.07
    POSITIVE LOGITS
     metabolites
    0.14
     compounds
    0.14
     cannabinoids
    0.13
     веществ
    0.13
     hydrochlor
    0.13
     neurotrans
    0.13
     toxins
    0.12
     substances
    0.12
     sugars
    0.12
     serotonin
    0.12
    Activations Density 0.144%

    No Known Activations