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. 129807
    Prev
    Next
    INDEX
    Explanations

    stats

    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
     jól
    -0.10
    erva
    -0.09
    186
    -0.08
    arkt
    -0.08
    _gateway
    -0.08
    jours
    -0.08
     wali
    -0.08
    Diary
    -0.07
     Dei
    -0.07
    曝光
    -0.07
    POSITIVE LOGITS
    [,]
    0.09
     décr
    0.08
    ের
    0.08
     dimin
    0.08
    פה
    0.08
    imul
    0.08
     détermin
    0.08
     постоян
    0.08
     влияние
    0.07
     peppers
    0.07
    Activations Density 0.003%

    No Known Activations