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. 76300
    Prev
    Next
    INDEX
    Explanations

    VR/AR tracking

    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
    .Binary
    -0.08
    98
    -0.08
     vitae
    -0.07
     presentations
    -0.07
     Habe
    -0.07
    harib
    -0.07
    -vis
    -0.07
     Tax
    -0.07
     revive
    -0.07
    chem
    -0.07
    POSITIVE LOGITS
     Tracking
    0.09
     tracking
    0.09
    Tracking
    0.09
     inaccuracies
    0.09
     trackers
    0.08
     felly
    0.08
    ยิง
    0.08
     מערכת
    0.08
     tracker
    0.08
    ન્ક
    0.08
    Activations Density 0.004%

    No Known Activations