Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43091
    Prev
    Next
    INDEX
    Explanations

    Just happened events

    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
     болады
    -0.08
    ayot
    -0.07
     начиная
    -0.07
     deviations
    -0.07
     кі
    -0.07
     heutzutage
    -0.07
     persistence
    -0.07
     outages
    -0.07
     Celtic
    -0.07
     experimentation
    -0.07
    POSITIVE LOGITS
    aneously
    0.09
     Aq
    0.09
     ਨੇ
    0.08
    ocracy
    0.08
    ,we
    0.08
    _arg
    0.08
    ,new
    0.08
    ürgen
    0.08
     Successfully
    0.08
    (New
    0.08
    Activations Density 0.039%

    No Known Activations