© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29374
    Prev
    Next
    INDEX
    Explanations

    multiply

    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
    .inventory
    -0.08
     lee
    -0.07
    akka
    -0.07
    .top
    -0.07
    도
    -0.07
    idai
    -0.07
    Oil
    -0.07
     empregado
    -0.07
     quelques
    -0.07
     எந்த
    -0.07
    POSITIVE LOGITS
    Ort
    0.08
     {{{
    0.08
    वाही
    0.08
     WOW
    0.08
     Playground
    0.08
    ീത
    0.08
     pensado
    0.07
     articul
    0.07
     appreciative
    0.07
     atract
    0.07
    Activations Density 0.173%

    No Known Activations