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. 11725
    Prev
    Next
    INDEX
    Explanations

    x

    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
    iray
    -0.09
    endforeach
    -0.08
     crystall
    -0.08
     발견
    -0.08
    ateway
    -0.08
    总部
    -0.08
     lax
    -0.08
    onden
    -0.08
     uncomplicated
    -0.07
     ly
    -0.07
    POSITIVE LOGITS
     pixels
    0.10
    Pixel
    0.09
     anime
    0.09
     pixel
    0.09
    Pixels
    0.08
     presets
    0.08
     Pixel
    0.08
     freezes
    0.08
    128
    0.08
     framebuffer
    0.08
    Activations Density 0.007%

    No Known Activations