© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2510
    Prev
    Next
    INDEX
    Explanations

    grandeur

    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
     дра
    -0.08
     боя
    -0.08
     הכר
    -0.08
     Xen
    -0.08
    आ
    -0.08
     DHS
    -0.07
    Roll
    -0.07
    慎
    -0.07
     председ
    -0.07
     uname
    -0.07
    POSITIVE LOGITS
     NOTE
    0.10
     youthful
    0.08
     ial
    0.07
    /contracts
    0.07
    mittel
    0.07
     �
    0.07
     �
    0.07
     கூற
    0.07
     சம்ப
    0.07
     TOD
    0.07
    Activations Density 0.001%

    No Known Activations