© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24738
    Prev
    Next
    INDEX
    Explanations

    生成

    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
    изация
    -0.08
     Stranger
    -0.08
     tid
    -0.08
     Firms
    -0.08
     Zinc
    -0.08
    .mm
    -0.08
     Capsule
    -0.07
    agy
    -0.07
     Firm
    -0.07
    Tid
    -0.07
    POSITIVE LOGITS
     posed
    0.08
     floral
    0.08
     grasp
    0.08
     pict
    0.08
     edilen
    0.08
     dado
    0.07
    OLS
    0.07
     दिए
    0.07
     printable
    0.07
     pede
    0.07
    Activations Density 0.013%

    No Known Activations