Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 49816
    Prev
    Next
    INDEX
    Explanations

    -width

    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
     tick
    -0.08
     Mere
    -0.07
     analyze
    -0.07
    wax
    -0.07
     necessary
    -0.07
    ;)↵
    -0.07
    -0.07
     quốc
    -0.07
     missile
    -0.07
     boh
    -0.07
    POSITIVE LOGITS
     nastav
    0.08
     estab
    0.08
     VARCHAR
    0.08
    922
    0.08
    imum
    0.08
     Organic
    0.07
     Cable
    0.07
    863
    0.07
     ribs
    0.07
    CTA
    0.07
    Activations Density 0.001%

    No Known Activations