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. 23-RESID-POST-AA
    6. 130861
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _userdata
    -0.09
     Lear
    -0.09
    -aged
    -0.08
     Shooter
    -0.08
     learner
    -0.08
     learners
    -0.08
     Age
    -0.08
     Buyer
    -0.08
    Age
    -0.08
     Shoe
    -0.08
    POSITIVE LOGITS
     मन्त्र
    0.10
     concentration
    0.10
     visualization
    0.10
     concentración
    0.10
     man
    0.09
     concentração
    0.09
    asm
    0.09
     alarms
    0.09
     namar
    0.09
     yan
    0.09
    Activations Density 0.007%

    No Known Activations