© 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. 99515
    Prev
    Next
    INDEX
    Explanations

    respectively

    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
     مدرس
    -0.08
     Increasing
    -0.08
     entsprech
    -0.08
     Mede
    -0.07
    obre
    -0.07
     entsprechenden
    -0.07
     MMC
    -0.07
    окуп
    -0.07
    malar
    -0.07
    _possible
    -0.07
    POSITIVE LOGITS
     unquestionably
    0.09
     crowned
    0.08
     obviously
    0.07
     consolation
    0.07
     drawback
    0.07
     coun
    0.07
    /basic
    0.07
    坪
    0.07
     juggling
    0.07
     undoubtedly
    0.07
    Activations Density 0.004%

    No Known Activations