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. 43126
    Prev
    Next
    INDEX
    Explanations

    cleaning and polishing

    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
     seed
    -0.09
     Provision
    -0.08
    seed
    -0.08
     provision
    -0.08
    (
    -0.07
     (
    -0.07
    巨大
    -0.07
     crucial
    -0.07
    論
    -0.07
    Seed
    -0.07
    POSITIVE LOGITS
     microfiber
    0.10
     поверхности
    0.10
     upholstery
    0.10
     countertop
    0.10
     चम
    0.09
     chiffon
    0.09
     bezel
    0.09
     doek
    0.09
     oppervlak
    0.09
     silicone
    0.09
    Activations Density 0.025%

    No Known Activations