© 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 EvalsExportsinterp-engineNEWAPI 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. 110593
    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
    cas
    -0.08
     tac
    -0.08
     transferred
    -0.07
    "?↵↵
    -0.07
     wouldn
    -0.07
    okra
    -0.07
    -0.07
    "↵↵//
    -0.07
    ?”↵↵
    -0.07
     weiß
    -0.07
    POSITIVE LOGITS
     paragraphs
    0.11
     paragraph
    0.10
     subsection
    0.10
     подробно
    0.10
     discuss
    0.10
     Paragraph
    0.10
     مخت
    0.09
     подробнее
    0.09
     besproken
    0.09
    Paragraph
    0.09
    Activations Density 0.062%
    No Known Activations