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. 111995
    Prev
    Next
    INDEX
    Explanations

    =

    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
    ileno
    -0.09
    _BT
    -0.08
    .loaded
    -0.08
    _sz
    -0.07
     हे
    -0.07
    _am
    -0.07
    otyping
    -0.07
     induced
    -0.07
    .single
    -0.07
    _da
    -0.07
    POSITIVE LOGITS
     MIG
    0.07
    дері
    0.07
     Mig
    0.07
     poseb
    0.07
    дерін
    0.07
     unrhyw
    0.07
     комбина
    0.07
     Raim
    0.07
    ுக்
    0.07
     ави
    0.07
    Activations Density 0.125%

    No Known Activations