© 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. 47182
    Prev
    Next
    INDEX
    Explanations

    guide

    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
    Pant
    -0.09
     Uhr
    -0.08
    CED
    -0.07
     ge
    -0.07
     Jaime
    -0.07
     Jones
    -0.07
    most
    -0.07
    轨
    -0.07
     Pant
    -0.07
    Hull
    -0.07
    POSITIVE LOGITS
     发布
    0.09
     curta
    0.08
     herunterladen
    0.08
    .md
    0.08
     Польз
    0.08
     veröff
    0.08
    /blog
    0.08
     thor
    0.07
     courte
    0.07
     তৈ
    0.07
    Activations Density 0.014%

    No Known Activations