© 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. 11-RESID-POST-AA
    11. 79191
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reportedly
    -0.12
     apparently
    -0.12
     remarkably
    -0.09
     striking
    -0.09
     seemingly
    -0.08
     astonishing
    -0.08
     aparentemente
    -0.08
    arang
    -0.08
     Crushing
    -0.08
     supposedly
    -0.08
    POSITIVE LOGITS
     someday
    0.11
     algún
    0.11
     nějak
    0.10
     alguma
    0.10
     હશે
    0.10
     zumindest
    0.10
     alguna
    0.10
     qualche
    0.09
     algum
    0.09
     irgendwo
    0.09
    Activations Density 0.361%

    No Known Activations