© 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. 5596
    Prev
    Next
    INDEX
    Explanations

    say ":"

    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
    ാക്കി
    -0.09
    োট
    -0.09
    ിക്കുകയും
    -0.09
     vårt
    -0.08
     ქართული
    -0.08
    ಷ್ಟ
    -0.08
    ഷ്ട
    -0.08
     дак
    -0.08
     সকল
    -0.08
     հաստ
    -0.08
    POSITIVE LOGITS
    20
    0.10
    11
    0.09
    22
    0.09
    23
    0.09
    17
    0.09
    _CA
    0.08
    14
    0.08
    36
    0.08
    _CD
    0.08
    _RS
    0.08
    Activations Density 0.008%

    No Known Activations