© 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. 7-RESID-POST-AA
    11. 1422
    Prev
    Next
    INDEX
    Explanations

    around

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prolific
    -0.08
    cią
    -0.08
     tweeted
    -0.07
     pending
    -0.07
     }))↵
    -0.07
    502
    -0.07
     commands
    -0.07
     scanned
    -0.07
     bpy
    -0.07
     Kow
    -0.07
    POSITIVE LOGITS
     overpriced
    0.08
     कीमत
    0.08
     pare
    0.08
    .symmetric
    0.08
    寻找
    0.08
     กัน
    0.08
     presidencial
    0.08
     धो
    0.08
    иций
    0.08
     رح
    0.08
    Activations Density 0.008%

    No Known Activations