Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54099
    Prev
    Next
    INDEX
    Explanations

    Getting ready

    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
    તો
    -0.08
    dep
    -0.08
    τα
    -0.08
    ತನ
    -0.08
     keçir
    -0.07
    coes
    -0.07
     قو
    -0.07
    -0.07
    *_
    -0.07
    DE
    -0.07
    POSITIVE LOGITS
    閱讀
    0.09
     즐
    0.09
     disfrutar
    0.08
     Lesen
    0.08
    !↵↵
    0.08
     aventura
    0.08
     unforgettable
    0.08
    !↵
    0.08
     긴
    0.08
     kidding
    0.08
    Activations Density 0.019%

    No Known Activations