© 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. 3-RESID-POST-AA
    11. 2653
    Prev
    Next
    INDEX
    Explanations

    and

    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
     נוס
    -0.08
     Далее
    -0.08
     Offices
    -0.07
    后的
    -0.07
    创业
    -0.07
    ategy
    -0.07
    [ch
    -0.07
     dictum
    -0.07
     �
    -0.07
    겠다
    -0.07
    POSITIVE LOGITS
     bia
    0.08
     incapable
    0.07
     accent
    0.07
    Float
    0.07
     tal
    0.07
     прид
    0.07
     TIP
    0.07
    ser
    0.07
    anze
    0.07
    TT
    0.07
    Activations Density 0.230%

    No Known Activations