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. 15-RESID-POST-AA
    6. 19115
    Prev
    Next
    INDEX
    Explanations

    Foreign word "very"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.08
     :
    -0.08
     falsch
    -0.07
     certos
    -0.07
     Innovation
    -0.07
     Battles
    -0.07
     innovation
    -0.07
     thêm
    -0.07
    SIDE
    -0.07
     lorsque
    -0.07
    POSITIVE LOGITS
     evidenced
    0.11
     للغاية
    0.10
     penuh
    0.10
    ,因此
    0.10
     جدًا
    0.10
     sosai
    0.10
     ولذلك
    0.09
    fully
    0.09
     جداً
    0.09
     ולכן
    0.09
    Activations Density 0.122%

    No Known Activations