© 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. 23-RESID-POST-AA
    11. 6451
    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
     relying
    -0.08
     Makes
    -0.08
     metabolism
    -0.08
     gezondheid
    -0.08
    éns
    -0.08
     ರಸ್ತ
    -0.08
    Variance
    -0.07
     irrespons
    -0.07
     organisme
    -0.07
     করবে
    -0.07
    POSITIVE LOGITS
     limit
    0.14
    Limit
    0.13
     discontinue
    0.13
     avoid
    0.13
    limit
    0.12
    _limit
    0.12
     Limit
    0.12
     избег
    0.12
     monitor
    0.11
    避免
    0.11
    Activations Density 0.020%

    No Known Activations