© 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. 63337
    Prev
    Next
    INDEX
    Explanations

    decreasing, slowing down

    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
     представляет
    -0.08
     viewers
    -0.07
     ವರ
    -0.07
     ترتیب
    -0.07
     suitcase
    -0.07
    ينا
    -0.07
     Comprehensive
    -0.07
     сайт
    -0.07
     Б
    -0.07
    osit
    -0.07
    POSITIVE LOGITS
     slows
    0.10
     ralent
    0.09
     nearing
    0.09
     slowing
    0.09
     diminishing
    0.09
     dismin
    0.08
     dificult
    0.08
     eas
    0.08
     aumentar
    0.08
     steadily
    0.08
    Activations Density 0.028%

    No Known Activations