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. 11-RESID-POST-AA
    6. 106025
    Prev
    Next
    INDEX
    Explanations

    multi-path networking

    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
    rono
    -0.08
    -0.08
     pagbab
    -0.07
     변화
    -0.07
     apoyar
    -0.07
    kw
    -0.07
    igsaw
    -0.07
    modules
    -0.07
     respectful
    -0.07
     scope
    -0.07
    POSITIVE LOGITS
     kako
    0.08
    -ма
    0.08
    备用
    0.08
    ुलाई
    0.08
    査
    0.08
     arb
    0.07
     Pule
    0.07
    策略
    0.07
    渠道
    0.07
     clogged
    0.07
    Activations Density 0.007%

    No Known Activations