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. 78613
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    ャン
    -0.09
     данных
    -0.08
    .xpath
    -0.08
     chit
    -0.08
    	values
    -0.08
     اللون
    -0.08
    icuous
    -0.08
     التأ
    -0.08
     किस
    -0.07
    (IP
    -0.07
    POSITIVE LOGITS
     presque
    0.08
     quase
    0.07
     situations
    0.07
     profesión
    0.07
     classrooms
    0.07
    ofil
    0.07
     almost
    0.07
     ancient
    0.07
     hospice
    0.07
    逆
    0.07
    Activations Density 0.073%

    No Known Activations