© 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. 3-RESID-POST-AA
    11. 12901
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Han
    -0.08
     cari
    -0.08
     fal
    -0.08
    Lvl
    -0.08
     agr
    -0.08
    群
    -0.07
    用途
    -0.07
     eng
    -0.07
     yol
    -0.07
     Grou
    -0.07
    POSITIVE LOGITS
     Eden
    0.08
     motel
    0.07
     blends
    0.07
     HOME
    0.07
     корпоратив
    0.07
     Ged
    0.07
    IDE
    0.07
     Erschein
    0.07
    法规
    0.07
    hy
    0.07
    Activations Density 0.053%

    No Known Activations