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. 11867
    Prev
    Next
    INDEX
    Explanations

    as a

    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
    Marshal
    -0.08
     Jasper
    -0.08
     oppose
    -0.08
     magnifique
    -0.08
     chauff
    -0.07
    كذا
    -0.07
     PLA
    -0.07
    academ
    -0.07
     Martins
    -0.07
     Maur
    -0.07
    POSITIVE LOGITS
    用途
    0.08
     сар
    0.08
    境
    0.08
     overloaded
    0.08
    ોસ
    0.07
     unless
    0.07
     ген
    0.07
    ôsob
    0.07
     гол
    0.07
     talking
    0.07
    Activations Density 0.009%

    No Known Activations