© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43546
    Prev
    Next
    INDEX
    Explanations

    eye

    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
    -0.07
     Laser
    -0.07
     Magnesium
    -0.07
    CRI
    -0.07
    ’énergie
    -0.07
     энерг
    -0.07
     enerji
    -0.07
     Energ
    -0.07
     интер
    -0.07
     hell
    -0.07
    POSITIVE LOGITS
     disturbed
    0.08
     আক্রান্ত
    0.08
     위해
    0.08
    ոն
    0.08
     solitary
    0.08
    anship
    0.07
     wandered
    0.07
    bu
    0.07
    존
    0.07
     survived
    0.07
    Activations Density 0.004%
    No Known Activations