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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 49245
    Prev
    Next
    INDEX
    Explanations

    Lilac

    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
     Renaissance
    -0.08
    偿
    -0.08
     Madonna
    -0.08
    Rn
    -0.08
    IPMENT
    -0.07
     Tast
    -0.07
     جز
    -0.07
     tast
    -0.07
    parking
    -0.07
    الات
    -0.07
    POSITIVE LOGITS
    .vector
    0.10
    .Validation
    0.09
    -alert
    0.08
    .handle
    0.08
    чики
    0.08
     Дев
    0.08
    ки
    0.08
    чик
    0.08
    .validate
    0.08
    вав
    0.08
    Activations Density 0.009%

    No Known Activations