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. 76769
    Prev
    Next
    INDEX
    Explanations

    turns

    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
     establishment
    -0.07
     usage
    -0.07
    िस्ट
    -0.07
     mód
    -0.07
     intervals
    -0.07
    יסט
    -0.07
     disruption
    -0.07
     syndrome
    -0.07
     strains
    -0.07
    签
    -0.07
    POSITIVE LOGITS
     দাঁ
    0.10
     Janu
    0.09
     apolog
    0.09
     возле
    0.09
     রেখে
    0.09
     তাক
    0.09
     apologized
    0.09
    ,看
    0.09
    来看
    0.08
    面对
    0.08
    Activations Density 0.008%

    No Known Activations