© 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. 91629
    Prev
    Next
    INDEX
    Explanations

    structured text

    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
     inert
    -0.09
     dirs
    -0.07
    .nav
    -0.07
     inclin
    -0.07
     (?)
    -0.07
    xin
    -0.07
    'i
    -0.07
     labeled
    -0.07
     typed
    -0.07
     ephemeral
    -0.07
    POSITIVE LOGITS
     bustling
    0.10
     حیر
    0.10
    Wonder
    0.10
    不仅
    0.10
     hustle
    0.09
    值得
    0.09
     groundbreaking
    0.09
    Ladies
    0.09
    FAQs
    0.09
     fascinating
    0.09
    Activations Density 0.057%

    No Known Activations