© 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. 108261
    Prev
    Next
    INDEX
    Explanations

    teams

    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
     मी
    -0.09
     אס
    -0.08
    แก
    -0.08
    attar
    -0.08
     çöz
    -0.08
     संश
    -0.08
     ए
    -0.08
     сцен
    -0.07
     الإ
    -0.07
    ริ
    -0.07
    POSITIVE LOGITS
    -ons
    0.08
     perspectives
    0.08
    Perspective
    0.08
     Perspectives
    0.08
    -Se
    0.08
     Referential
    0.08
     vantage
    0.08
     hous
    0.07
     Katy
    0.07
     Occidental
    0.07
    Activations Density 0.022%

    No Known Activations