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. 53893
    Prev
    Next
    INDEX
    Explanations

    tings

    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
    irho
    -0.08
    viewport
    -0.08
     briefing
    -0.08
    iett
    -0.08
    .urlopen
    -0.07
     בזמן
    -0.07
     airt
    -0.07
    liv
    -0.07
     ומ
    -0.07
    handlung
    -0.07
    POSITIVE LOGITS
    复制
    0.12
     cloning
    0.12
     кл
    0.11
    _clone
    0.11
     clones
    0.11
     reproduction
    0.10
    clone
    0.10
     copies
    0.10
     clon
    0.10
    コピー
    0.10
    Activations Density 0.007%

    No Known Activations