© 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. 3-RESID-POST-AA
    11. 13403
    Prev
    Next
    INDEX
    Explanations

    swelling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ಪ್ರಸ
    -0.08
     interceptions
    -0.07
    inaries
    -0.07
     successive
    -0.07
    _gu
    -0.07
    zeit
    -0.07
     Hale
    -0.07
    _im
    -0.07
    筑
    -0.07
    letters
    -0.07
    POSITIVE LOGITS
     tendencies
    0.08
    �
    0.08
     Tav
    0.08
     lên
    0.08
     Stahl
    0.08
     возникает
    0.07
     થઈ
    0.07
     LARGE
    0.07
     тво
    0.07
    ાભ
    0.07
    Activations Density 0.065%

    No Known Activations