© 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. 112327
    Prev
    Next
    INDEX
    Explanations

    Instructions and settings

    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
     problem
    -0.08
     ụgwọ
    -0.08
    ========
    -0.08
    =======
    -0.08
    CL
    -0.07
     precaution
    -0.07
     _;↵
    -0.07
     CL
    -0.07
    sstream
    -0.07
     Compensation
    -0.07
    POSITIVE LOGITS
     vừa
    0.09
     resembling
    0.09
     вроде
    0.09
    >((
    0.08
     waarbij
    0.08
    属于
    0.08
     này
    0.08
     שלא
    0.08
     whose
    0.08
     designed
    0.08
    Activations Density 0.465%

    No Known Activations