© 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. 63974
    Prev
    Next
    INDEX
    Explanations

    "too good to be true"

    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
    elateerde
    -0.09
     رشته
    -0.08
    ikiwa
    -0.08
    pts
    -0.08
     workload
    -0.07
     wealth
    -0.07
     Wealth
    -0.07
    ��
    -0.07
    ��
    -0.07
    -0.07
    POSITIVE LOGITS
     слишком
    0.09
     demasiado
    0.09
     liian
    0.09
    oren
    0.09
     너무
    0.08
     Too
    0.08
     lest
    0.08
     Programm
    0.08
     */
↵
    0.08
     schad
    0.08
    Activations Density 0.005%
    No Known Activations