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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112981
    Prev
    Next
    INDEX
    Explanations

    (x

    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
    力度
    -0.09
    ും
    -0.09
    算盘
    -0.08
    usebenza
    -0.08
     artes
    -0.08
     bedrijven
    -0.08
    反水
    -0.08
     रस
    -0.07
    -options
    -0.07
    球队
    -0.07
    POSITIVE LOGITS
     incremental
    0.08
    .tm
    0.08
    Increment
    0.07
    ired
    0.07
    abr
    0.07
    _MAG
    0.07
     +
    0.07
     Clair
    0.07
    UNDER
    0.07
    increment
    0.07
    Activations Density 0.034%

    No Known Activations