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. 15-RESID-POST-AA
    6. 19669
    Prev
    Next
    INDEX
    Explanations

    sealing drafts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Redis
    -0.08
    .Annotation
    -0.08
     Trustees
    -0.08
    always
    -0.08
     socialist
    -0.08
     socialism
    -0.08
     Always
    -0.07
     lives
    -0.07
     lifes
    -0.07
     trustees
    -0.07
    POSITIVE LOGITS
    漏洞
    0.15
     airtight
    0.12
     отверст
    0.12
     leaks
    0.12
     vulnerabilities
    0.12
    Leaks
    0.11
    遗漏
    0.11
     looph
    0.11
     tocht
    0.11
    漏
    0.11
    Activations Density 0.014%

    No Known Activations