© 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. 75796
    Prev
    Next
    INDEX
    Explanations

    Module pattern

    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
     affected
    -0.09
    herited
    -0.09
    ophon
    -0.09
    egal
    -0.08
     faithful
    -0.08
     kosher
    -0.08
     inherited
    -0.07
    affected
    -0.07
    -0.07
    rating
    -0.07
    POSITIVE LOGITS
     runoff
    0.08
    ોથી
    0.08
    الن
    0.08
     vereadores
    0.08
    中王
    0.08
    larından
    0.08
    ondo
    0.08
     escritores
    0.07
     WON
    0.07
     WWF
    0.07
    Activations Density 0.001%

    No Known Activations