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. 45855
    Prev
    Next
    INDEX
    Explanations

    value, keys, queries

    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
    multipart
    -0.08
    olly
    -0.08
     consac
    -0.08
     Multipart
    -0.08
     multipart
    -0.08
     పవ
    -0.08
    ustu
    -0.07
    Cad
    -0.07
    (blank
    -0.07
     underserved
    -0.07
    POSITIVE LOGITS
     heter
    0.08
    141
    0.08
    694
    0.08
     بيت
    0.08
     "@/
    0.08
     vít
    0.08
     денежных
    0.08
     Antonio
    0.07
     inteligencia
    0.07
     Eta
    0.07
    Activations Density 0.002%

    No Known Activations