© 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. 47540
    Prev
    Next
    INDEX
    Explanations

    て

    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
    ober
    -0.09
     Recep
    -0.08
     Savannah
    -0.08
     yaptı
    -0.08
     heavy
    -0.08
     inbound
    -0.08
     भारी
    -0.08
     heavily
    -0.08
    need
    -0.08
    했고
    -0.07
    POSITIVE LOGITS
    :Array
    0.07
     Greatest
    0.07
    .Execute
    0.07
    ':''
    0.07
     IS
    0.07
     Kon
    0.07
    IS
    0.07
     Bell
    0.07
    .tech
    0.07
     Biel
    0.07
    Activations Density 0.002%

    No Known Activations