© 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. 29076
    Prev
    Next
    INDEX
    Explanations

    Arrows

    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
     pensent
    -0.09
    terminate
    -0.09
     Sympt
    -0.08
     -↵↵
    -0.08
     праблем
    -0.08
     godz
    -0.08
     문제
    -0.08
     लड़
    -0.08
     exem
    -0.08
     সমস্য
    -0.08
    POSITIVE LOGITS
     mezz
    0.08
     Friedrich
    0.07
    fre
    0.07
    _media
    0.07
    IVA
    0.07
     pl
    0.07
     tailored
    0.07
     mobile
    0.07
    mob
    0.07
    F
    0.07
    Activations Density 0.001%

    No Known Activations