© 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. 129330
    Prev
    Next
    INDEX
    Explanations

    graph theory theorems

    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
     baby's
    -0.08
    nav
    -0.08
    ાઈન
    -0.08
     casts
    -0.08
    абар
    -0.08
    Taste
    -0.08
     personalmente
    -0.08
    ાઇન
    -0.08
    ાસ
    -0.07
    aan
    -0.07
    POSITIVE LOGITS
    允
    0.09
     forbid
    0.08
     paras
    0.08
     forb
    0.08
     maximal
    0.08
     maxim
    0.07
    最大
    0.07
    maximize
    0.07
    限
    0.07
    =max
    0.07
    Activations Density 0.009%

    No Known Activations