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. 112005
    Prev
    Next
    INDEX
    Explanations

    inside

    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
     പ്ല
    -0.08
     thousands
    -0.08
    .connected
    -0.08
    lera
    -0.08
     വഴി
    -0.08
    ульта
    -0.08
     വിവിധ
    -0.08
    connected
    -0.08
     ബന്ധപ്പെട്ട
    -0.07
    ousands
    -0.07
    POSITIVE LOGITS
     sco
    0.10
     Chavez
    0.08
    _inside
    0.08
    Madrid
    0.08
     içinde
    0.08
     ভিত
    0.08
     cushions
    0.08
     nestled
    0.08
    ిండ
    0.08
     coax
    0.08
    Activations Density 0.012%

    No Known Activations