Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 43896
    Prev
    Next
    INDEX
    Explanations

    merging files

    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
     загад
    -0.08
    落实
    -0.08
     depreciation
    -0.07
     grips
    -0.07
     nghi
    -0.07
    anku
    -0.07
    Rev
    -0.07
    Withdrawal
    -0.07
    atanga
    -0.07
     frightened
    -0.07
    POSITIVE LOGITS
     merging
    0.21
     Merge
    0.19
     объедин
    0.19
     concaten
    0.19
    .merge
    0.19
     merge
    0.19
     concatenate
    0.19
    .concatenate
    0.18
    Merge
    0.18
     merger
    0.18
    Activations Density 0.024%

    No Known Activations