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. 43339
    Prev
    Next
    INDEX
    Explanations

    cube volumes

    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
    bundle
    -0.10
    ồng
    -0.09
     bundle
    -0.08
    emons
    -0.08
    Getting
    -0.08
    ähler
    -0.08
    stk
    -0.07
    uhe
    -0.07
    emde
    -0.07
    lang
    -0.07
    POSITIVE LOGITS
     expuls
    0.09
     caps
    0.08
    _caps
    0.07
     النات
    0.07
     закон
    0.07
     cork
    0.07
    (Component
    0.07
     holog
    0.07
     comprend
    0.07
     bijvoorbeeld
    0.07
    Activations Density 0.035%

    No Known Activations