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. 13046
    Prev
    Next
    INDEX
    Explanations

    code-related numbers

    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
     Erasmus
    -0.08
    еком
    -0.08
     redd
    -0.07
     STR
    -0.07
     STEP
    -0.07
    spath
    -0.07
    astre
    -0.07
     breathtaking
    -0.07
     pk
    -0.07
     euren
    -0.07
    POSITIVE LOGITS
    .Full
    0.08
     জ
    0.07
     મેળ
    0.07
     Crawford
    0.07
    ull
    0.07
    0.07
    253
    0.07
     સા�
    0.07
    ender
    0.07
     bail
    0.07
    Activations Density 0.006%

    No Known Activations