© 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. 45422
    Prev
    Next
    INDEX
    Explanations

    code-related true statements

    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
     did
    -0.08
    kel
    -0.08
    Requirement
    -0.08
    ajana
    -0.07
     रात
    -0.07
    /environment
    -0.07
    Especially
    -0.07
     salts
    -0.07
    Did
    -0.07
     perch
    -0.07
    POSITIVE LOGITS
    关于
    0.09
    有什么
    0.08
     Aussagen
    0.08
     envel
    0.08
     bezüglich
    0.08
     Reihen
    0.08
     Sod
    0.08
    ένα
    0.07
     Reflex
    0.07
     Bünd
    0.07
    Activations Density 0.043%

    No Known Activations