© 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. 44673
    Prev
    Next
    INDEX
    Explanations

    continue

    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
     frontline
    -0.08
     eficaz
    -0.07
    ayer
    -0.07
     complexities
    -0.07
     temel
    -0.07
     preced
    -0.07
     जु
    -0.07
     इंटर
    -0.07
     उल्लेख
    -0.07
     Could
    -0.07
    POSITIVE LOGITS
     дальше
    0.11
     hacia
    0.10
     pokrač
    0.10
     dalej
    0.10
    继续
    0.09
     aż
    0.09
    直到
    0.09
    tow
    0.09
    unin
    0.09
     lleg
    0.09
    Activations Density 0.014%

    No Known Activations