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. 42137
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     rekening
    -0.07
    assert
    -0.07
     값을
    -0.07
    	assert
    -0.07
     valley
    -0.07
    .Value
    -0.07
    Phones
    -0.06
     kenn
    -0.06
     Assert
    -0.06
    Trav
    -0.06
    POSITIVE LOGITS
     hierfür
    0.09
     зэрэг
    0.08
     געפ
    0.08
    endez
    0.08
    ظار
    0.08
    وف
    0.08
    र्तमान
    0.08
    иболее
    0.08
    irgí
    0.08
    ειτουργ
    0.08
    Activations Density 0.048%

    No Known Activations