© 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. 30837
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    rede
    -0.08
    herlands
    -0.08
    ccan
    -0.08
    _prof
    -0.08
    顿
    -0.08
     الأم
    -0.08
     кезде
    -0.08
     �
    -0.07
    _common
    -0.07
    ခဲ့
    -0.07
    POSITIVE LOGITS
    都有
    0.10
    क्र
    0.08
     alike
    0.08
     hinweg
    0.07
     Karin
    0.07
     gaar
    0.07
     sigma
    0.07
     равно
    0.07
     puisse
    0.07
     Mitar
    0.07
    Activations Density 0.039%

    No Known Activations