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. 56106
    Prev
    Next
    INDEX
    Explanations

    percentage calculations and comparisons

    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
     Pietro
    -0.08
     descend
    -0.08
     Gavin
    -0.08
     Gide
    -0.08
    Intersect
    -0.07
    983
    -0.07
     màu
    -0.07
    -haired
    -0.07
     आते
    -0.07
     xsi
    -0.07
    POSITIVE LOGITS
    iation
    0.08
    行为
    0.08
    ulus
    0.08
    tributor
    0.08
    stk
    0.07
    imum
    0.07
     مثال
    0.07
     confused
    0.07
    Boost
    0.07
    through
    0.07
    Activations Density 0.028%

    No Known Activations