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. 117587
    Prev
    Next
    INDEX
    Explanations

    science and technology

    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
    ipping
    -0.08
    cult
    -0.08
    abit
    -0.08
    asp
    -0.08
    distinct
    -0.07
     NP
    -0.07
     acquired
    -0.07
     triv
    -0.07
     angel
    -0.07
    Ctrl
    -0.07
    POSITIVE LOGITS
     formula
    0.11
    公式
    0.11
     सूत्र
    0.11
     formulas
    0.10
    _formula
    0.09
    制度
    0.09
     formulation
    0.09
    formula
    0.08
     fórmula
    0.08
     공식
    0.08
    Activations Density 0.009%

    No Known Activations