© 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. 7-RESID-POST-AA
    11. 1374
    Prev
    Next
    INDEX
    Explanations

    five

    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
    多年
    -0.08
    ordin
    -0.08
    다는
    -0.07
     terminated
    -0.07
    每日
    -0.07
    ieties
    -0.07
    plings
    -0.07
    idden
    -0.07
    意味着
    -0.07
    pling
    -0.07
    POSITIVE LOGITS
     DAR
    0.08
     blanket
    0.08
     Rubber
    0.08
     DY
    0.08
     bamb
    0.07
     GU
    0.07
     Po
    0.07
    0.07
     RTT
    0.07
     NSK
    0.07
    Activations Density 0.008%
    No Known Activations