© 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. 44854
    Prev
    Next
    INDEX
    Explanations

    wave propagation

    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
    Dos
    -0.08
    Arts
    -0.08
     sunn
    -0.08
     accountable
    -0.08
    Ano
    -0.08
    ặn
    -0.08
     curated
    -0.08
     arts
    -0.08
    quem
    -0.07
     accountability
    -0.07
    POSITIVE LOGITS
     propagation
    0.19
    传播
    0.17
     propagate
    0.16
    Propagation
    0.15
     propag
    0.14
     waves
    0.14
     wave
    0.13
    速度
    0.13
     travels
    0.12
     ripple
    0.12
    Activations Density 0.017%

    No Known Activations