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. 106153
    Prev
    Next
    INDEX
    Explanations

    de

    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
    usus
    -0.09
     ibn
    -0.08
     jihad
    -0.07
    _sel
    -0.07
     vigueur
    -0.07
     vowel
    -0.07
     kullanılan
    -0.07
     Abend
    -0.07
     scoop
    -0.07
    ophobic
    -0.07
    POSITIVE LOGITS
     kaart
    0.09
    kaart
    0.09
    牌
    0.09
    板
    0.09
    เล็ต
    0.08
     карту
    0.08
     platter
    0.08
    盒
    0.08
    号码
    0.08
    カード
    0.08
    Activations Density 0.035%

    No Known Activations