© 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. 1248
    Prev
    Next
    INDEX
    Explanations

    ари

    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
    oted
    -0.07
     Bath
    -0.07
    ทะ
    -0.07
     Odd
    -0.07
     ak
    -0.07
    aware
    -0.07
    Dates
    -0.07
    represented
    -0.07
    certainty
    -0.07
     aandacht
    -0.07
    POSITIVE LOGITS
     �
    0.08
     Trier
    0.08
     saine
    0.08
     eig
    0.07
     ёсць
    0.07
    .optim
    0.07
    സ്
    0.07
    �
    0.07
    �
    0.07
    Neo
    0.07
    Activations Density 0.005%

    No Known Activations