© 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. 23-RESID-POST-AA
    11. 6141
    Prev
    Next
    INDEX
    Explanations

    SDK

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     systèmes
    -0.09
     sistemas
    -0.09
     systemen
    -0.09
     sistemi
    -0.09
    _system
    -0.09
    Sistema
    -0.08
     Sistemas
    -0.08
     systems
    -0.08
     sistema
    -0.08
     système
    -0.08
    POSITIVE LOGITS
     SDK
    0.32
     sdk
    0.29
    SDK
    0.28
    _sdk
    0.26
    -sdk
    0.25
    /sdk
    0.25
    .sdk
    0.24
    Sdk
    0.24
    sdk
    0.24
    .SDK
    0.23
    Activations Density 0.048%

    No Known Activations