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. 76746
    Prev
    Next
    INDEX
    Explanations

    Office

    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
    hy
    -0.09
    termin
    -0.08
     بد
    -0.08
     quanto
    -0.07
     longo
    -0.07
     chopping
    -0.07
     ale
    -0.07
    formations
    -0.07
     laundering
    -0.07
    -à
    -0.07
    POSITIVE LOGITS
    _fname
    0.08
    指出
    0.08
     તપાસ
    0.08
    さん
    0.07
    县
    0.07
    (validate
    0.07
     arcu
    0.07
     izv
    0.07
    数据显示
    0.07
    镜
    0.07
    Activations Density 0.059%

    No Known Activations