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. 113955
    Prev
    Next
    INDEX
    Explanations

    ly

    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
    عديد
    -0.09
     testify
    -0.08
    .question
    -0.07
     হতে
    -0.07
    岳
    -0.07
     состо
    -0.07
     Licensed
    -0.07
     અનેક
    -0.07
    alui
    -0.07
    sir
    -0.07
    POSITIVE LOGITS
     ";↵
    0.09
    ach
    0.08
     ";
    ↵
    0.08
     
    0.08
    ără
    0.07
    brief
    0.07
     kreativ
    0.07
    ень
    0.07
     insert
    0.07
    ...",↵
    0.07
    Activations Density 0.004%

    No Known Activations