© 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. 2629
    Prev
    Next
    INDEX
    Explanations

    ераль

    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
     stap
    -0.08
    KV
    -0.07
     greatness
    -0.07
    oxia
    -0.07
    끼
    -0.07
     Received
    -0.07
    orna
    -0.07
    -inner
    -0.07
     royal
    -0.07
     parallèle
    -0.07
    POSITIVE LOGITS
     auc
    0.08
    coord
    0.07
     ಕಾರ
    0.07
     внед
    0.07
     ANI
    0.07
     ó
    0.07
     Wein
    0.07
     ed
    0.07
     haus
    0.07
     silica
    0.07
    Activations Density 0.004%

    No Known Activations