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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12781
    Prev
    Next
    INDEX
    Explanations

    approvals

    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
    거리
    -0.08
     relationships
    -0.08
     gepf
    -0.07
    Knowledge
    -0.07
    umen
    -0.07
     beliefs
    -0.07
     ignorance
    -0.07
     hist
    -0.07
     nieuwste
    -0.07
    λισ
    -0.07
    POSITIVE LOGITS
    批准
    0.19
    审批
    0.17
     Approval
    0.17
     approve
    0.16
     aprovação
    0.16
     approval
    0.16
     승인
    0.15
     aprobación
    0.15
     aprob
    0.15
     approves
    0.15
    Activations Density 0.059%

    No Known Activations