© 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. 1497
    Prev
    Next
    INDEX
    Explanations

    com

    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
     العامة
    -0.10
     الرسمية
    -0.09
    -track
    -0.08
    _track
    -0.08
    规
    -0.08
     trac
    -0.08
     الفض
    -0.08
    正规的
    -0.08
     Marty
    -0.08
     noun
    -0.07
    POSITIVE LOGITS
    remium
    0.09
    uyễn
    0.08
    chil
    0.08
     incid
    0.08
    mic
    0.07
     Microwave
    0.07
    ge
    0.07
     satellite
    0.07
     Institute
    0.07
    -ge
    0.07
    Activations Density 0.005%

    No Known Activations