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. 74895
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     contam
    -0.08
    િત
    -0.08
     안내
    -0.08
    ичних
    -0.08
     ajudá
    -0.07
     hō
    -0.07
     okaz
    -0.07
    भूम
    -0.07
    풍
    -0.07
     तेल
    -0.07
    POSITIVE LOGITS
     dissatisfied
    0.09
    さん
    0.09
     തന്റെ
    0.08
     ছিলেন
    0.08
    .vars
    0.08
    ’র
    0.08
     merasa
    0.08
    .Modules
    0.08
     தனது
    0.08
     rode
    0.08
    Activations Density 0.142%

    No Known Activations