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. 7-RESID-POST-AA
    6. 1905
    Prev
    Next
    INDEX
    Explanations

    tension

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    一次
    -0.08
    开心
    -0.08
    효
    -0.07
    次数
    -0.07
    时候
    -0.07
     scenario
    -0.07
    效
    -0.07
     Giul
    -0.07
    赚钱
    -0.07
    真实
    -0.07
    POSITIVE LOGITS
     Automatically
    0.08
     tribut
    0.08
     subtil
    0.08
     kev
    0.07
     Recl
    0.07
     বজ
    0.07
     automatically
    0.07
     dini
    0.07
     Slave
    0.07
    >().
    0.07
    Activations Density 0.001%

    No Known Activations