© 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. 31222
    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
    ांड
    -0.09
    上述
    -0.08
    ாச
    -0.08
     eigh
    -0.08
     المذك
    -0.08
    注明
    -0.08
    盒
    -0.08
     های
    -0.08
    评级
    -0.07
    achal
    -0.07
    POSITIVE LOGITS
     reclaim
    0.09
     scraps
    0.08
     Passion
    0.08
     honestly
    0.08
     Providence
    0.08
    …
    0.08
    😊
    0.08
    毕
    0.08
     supervising
    0.08
     pleasure
    0.07
    Activations Density 0.038%

    No Known Activations