© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102175
    Prev
    Next
    INDEX
    Explanations

    computer code snippets

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ío
    -0.09
     बाकी
    -0.09
    -0.09
     الـ
    -0.08
     reprim
    -0.08
    ん
    -0.08
     tão
    -0.08
    āda
    -0.08
     so
    -0.08
     else's
    -0.08
    POSITIVE LOGITS
    Changes
    0.09
    Linear
    0.08
    Places
    0.08
    _changes
    0.08
    Each
    0.08
     המקומ
    0.08
     birçok
    0.08
     fiecare
    0.08
    诺
    0.08
    ប
    0.08
    Activations Density 0.000%
    No Known Activations