© 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. 63350
    Prev
    Next
    INDEX
    Explanations

    weatherstripping and energy savings

    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
    ويت
    -0.08
    DBObject
    -0.08
    本金
    -0.08
     obligado
    -0.08
    \Fac
    -0.08
     Trag
    -0.08
     mandated
    -0.08
     Embassy
    -0.08
    ».↵↵
    -0.08
    �
    -0.08
    POSITIVE LOGITS
     pest
    0.10
     leaks
    0.09
     leakage
    0.08
     leak
    0.08
     door
    0.08
     complaints
    0.08
     discrepancies
    0.08
     cửa
    0.08
     discontinu
    0.08
     insulation
    0.08
    Activations Density 0.022%

    No Known Activations