Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1542
    Prev
    Next
    INDEX
    Explanations

    up

    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
    671
    -0.10
    ۇق
    -0.08
    q
    -0.08
     Jour
    -0.07
    ۇ
    -0.07
    坚定
    -0.07
    egen
    -0.07
     Fault
    -0.07
    igns
    -0.07
    Sig
    -0.07
    POSITIVE LOGITS
     paperwork
    0.10
    手续
    0.08
     sạch
    0.08
     Erschein
    0.08
     لغ
    0.08
    rede
    0.08
     snabbt
    0.08
    急
    0.08
    行政
    0.08
     سريع
    0.08
    Activations Density 0.016%

    No Known Activations