© 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. 201
    Prev
    Next
    INDEX
    Explanations

    permutations

    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
     അമ്മ
    -0.10
     शांत
    -0.09
     ഭാര്യ
    -0.09
     calming
    -0.08
     compassion
    -0.08
     Calm
    -0.08
     mamá
    -0.08
    妻
    -0.08
     Mum
    -0.08
    相信
    -0.08
    POSITIVE LOGITS
     factorial
    0.09
     lucrative
    0.08
    PPER
    0.08
    urile
    0.08
    ัตร
    0.08
     appetizers
    0.07
     sequencing
    0.07
     plating
    0.07
     Preparation
    0.07
     sizzling
    0.07
    Activations Density 0.021%

    No Known Activations