© 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. 129517
    Prev
    Next
    INDEX
    Explanations

    share

    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
     crimes
    -0.07
    rese
    -0.07
     separat
    -0.07
     hervor
    -0.07
    (Message
    -0.07
    ديد
    -0.07
     viewer
    -0.07
     viewers
    -0.07
    -0.06
     directly
    -0.06
    POSITIVE LOGITS
     אולי
    0.09
     　　　
    0.09
    hostname
    0.09
    Unnamed
    0.08
     შესაძლოა
    0.08
    ურდ
    0.08
    masının
    0.08
     운영
    0.08
     შესაძლებელია
    0.08
     bulate
    0.08
    Activations Density 0.008%
    No Known Activations