Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60595
    Prev
    Next
    INDEX
    Explanations

    heartbeat

    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
     impede
    -0.09
     Penguin
    -0.09
     phishing
    -0.08
     lingu
    -0.07
     сун
    -0.07
     Midland
    -0.07
     linguistic
    -0.07
     అలాగే
    -0.07
     Qualified
    -0.07
     পরিষ
    -0.07
    POSITIVE LOGITS
     rhythms
    0.15
     rhythm
    0.13
     heartbeat
    0.13
    alive
    0.13
    beats
    0.12
    heartbeat
    0.12
    搏
    0.12
    生命
    0.12
    Heartbeat
    0.12
     alive
    0.11
    Activations Density 0.016%

    No Known Activations