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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77990
    Prev
    Next
    INDEX
    Explanations

    to

    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
    område
    -0.08
    området
    -0.08
    ACC
    -0.08
    缓
    -0.08
     Proposed
    -0.08
     Nue
    -0.07
     Applicable
    -0.07
    Libro
    -0.07
    -Step
    -0.07
     آرام
    -0.07
    POSITIVE LOGITS
     fooled
    0.09
     recognize
    0.09
     glance
    0.08
     distingu
    0.08
     trivial
    0.08
    onsense
    0.08
     очевид
    0.08
    มือ
    0.08
    基本
    0.08
     ви
    0.08
    Activations Density 0.060%

    No Known Activations