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. 12160
    Prev
    Next
    INDEX
    Explanations

    Id

    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
     Harvey
    -0.09
     amassed
    -0.08
    Arm
    -0.08
    -inf
    -0.08
     heavily
    -0.08
     Denken
    -0.08
     Sheldon
    -0.08
    ουν
    -0.08
     striking
    -0.08
     Botan
    -0.08
    POSITIVE LOGITS
    Pix
    0.08
     etiquetas
    0.08
     gang
    0.07
     tbody
    0.07
     conta
    0.07
     hone
    0.07
    nam
    0.07
    DOMContent
    0.07
     HTMLElement
    0.07
    Tween
    0.07
    Activations Density 0.001%

    No Known Activations