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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52801
    Prev
    Next
    INDEX
    Explanations

    early earth origins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VAT
    -0.08
    取消
    -0.08
     enqu
    -0.08
     +/-
    -0.08
    र्स
    -0.08
    成绩
    -0.08
     GDPR
    -0.08
    สอบ
    -0.08
    International
    -0.07
     offsetof
    -0.07
    POSITIVE LOGITS
     frü
    0.10
     ابتد
    0.09
     اولیه
    0.09
     ஆரம்ப
    0.09
     शुरुआ
    0.09
     earliest
    0.09
     первые
    0.09
     алғашқы
    0.09
     microbial
    0.08
     founder
    0.08
    Activations Density 0.010%

    No Known Activations