Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 1891
    Prev
    Next
    INDEX
    Explanations

    Act

    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
     shin
    -0.08
    না
    -0.07
     hvor
    -0.07
     intertw
    -0.07
     залиш
    -0.07
    なん
    -0.07
     усп
    -0.07
     Seit
    -0.07
    ๆ
    -0.07
     molecular
    -0.07
    POSITIVE LOGITS
     손
    0.08
    epis
    0.07
    iters
    0.07
     Mainland
    0.07
    cione
    0.07
    esi
    0.07
    adığı
    0.07
     solicitor
    0.07
     ప్రస
    0.07
     figura
    0.07
    Activations Density 0.000%

    No Known Activations