© 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. 45402
    Prev
    Next
    INDEX
    Explanations

    assistant instructions

    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
     diter
    -0.08
    ophe
    -0.07
     أشهر
    -0.07
    AIza
    -0.07
     cele
    -0.07
     an
    -0.07
    ஒர
    -0.07
     utilizz
    -0.07
    APT
    -0.07
    ்�
    -0.07
    POSITIVE LOGITS
    pen
    0.08
     onderweg
    0.08
    .pen
    0.08
    (pin
    0.08
     Перед
    0.08
     সামনে
    0.07
     თავ
    0.07
     రె
    0.07
     રૂપ
    0.07
    're
    0.07
    Activations Density 0.101%

    No Known Activations