© 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. 68401
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
    -called
    -0.09
    ews
    -0.08
     isin
    -0.08
     Gegenteil
    -0.08
    ечного
    -0.07
    кач
    -0.07
     historical
    -0.07
     neke
    -0.07
    .ONE
    -0.07
     Fiscal
    -0.07
    POSITIVE LOGITS
    Prefixes
    0.08
     βο
    0.08
     giriş
    0.08
    Mc
    0.07
    特色
    0.07
    820
    0.07
     twenties
    0.07
    prefix
    0.07
    (prefix
    0.07
    områ
    0.07
    Activations Density 0.010%

    No Known Activations