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. 59970
    Prev
    Next
    INDEX
    Explanations

    .$

    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
     Lamb
    -0.09
    Exponent
    -0.08
     Diablo
    -0.08
    ullu
    -0.08
    länd
    -0.08
    holm
    -0.08
     admits
    -0.07
     twisting
    -0.07
    -cond
    -0.07
    Featuring
    -0.07
    POSITIVE LOGITS
     ancestral
    0.08
     перейти
    0.08
     sichern
    0.08
     واله
    0.08
     кл
    0.08
     سلسلة
    0.08
     связ
    0.07
    ಠ
    0.07
     оцен
    0.07
     لله
    0.07
    Activations Density 0.001%

    No Known Activations