© 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. 102577
    Prev
    Next
    INDEX
    Explanations

    uniqueness

    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
     opgenomen
    -0.09
     miks
    -0.08
     bö
    -0.08
     bookmaker
    -0.08
     לצד
    -0.08
     mixer
    -0.08
     mixers
    -0.08
     crawler
    -0.08
     wrapper
    -0.08
     discounted
    -0.08
    POSITIVE LOGITS
     uniquely
    0.13
     uniqueness
    0.12
     تعیین
    0.11
     eindeutig
    0.11
     unequiv
    0.10
     unique
    0.10
    不能为空
    0.10
    Unique
    0.10
    确定
    0.10
    unique
    0.10
    Activations Density 0.016%

    No Known Activations