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. 15-RESID-POST-AA
    6. 19592
    Prev
    Next
    INDEX
    Explanations

    Witty comebacks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     only
    -0.10
    ioc
    -0.08
     саме
    -0.08
     solace
    -0.08
     pouze
    -0.08
     of
    -0.07
     лише
    -0.07
     numerous
    -0.07
     raken
    -0.07
     القرآن
    -0.07
    POSITIVE LOGITS
    pped
    0.09
    nergie
    0.09
    .placeholder
    0.08
    ster
    0.08
     sedang
    0.08
    (progress
    0.08
    Heat
    0.08
     વધી
    0.08
    -progress
    0.08
     ऊर्जा
    0.08
    Activations Density 0.015%

    No Known Activations