© 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. 99310
    Prev
    Next
    INDEX
    Explanations

    Proofs about infinite primes

    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
    实体
    -0.08
    -|
    -0.07
     UIKit
    -0.07
     organizing
    -0.07
    组织
    -0.07
    客户
    -0.07
    具体
    -0.07
    详细
    -0.07
     teaming
    -0.07
     kahle
    -0.07
    POSITIVE LOGITS
     항상
    0.09
     einzigart
    0.08
    Proof
    0.08
     sorprender
    0.08
     이후
    0.08
     Antibi
    0.08
     nouve
    0.08
     vinos
    0.08
     flawed
    0.08
    .Pending
    0.08
    Activations Density 0.020%

    No Known Activations