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

    Neuronpedia

    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. 78182
    Prev
    Next
    INDEX
    Explanations

    数据

    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
    ränkt
    -0.09
    umerator
    -0.08
     stocking
    -0.08
     espac
    -0.08
    冻
    -0.08
    aisy
    -0.08
     Lisp
    -0.08
    钢
    -0.08
     tær
    -0.08
    schaft
    -0.08
    POSITIVE LOGITS
     obra
    0.08
     технологии
    0.08
     analytics
    0.08
     enabled
    0.08
    -enabled
    0.07
     fuels
    0.07
     prihod
    0.07
     Analytics
    0.07
     actionable
    0.07
     perfil
    0.07
    Activations Density 0.005%

    No Known Activations