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. 58421
    Prev
    Next
    INDEX
    Explanations

    2

    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
    Aud
    -0.08
    ůj
    -0.08
    Stencil
    -0.08
     safety
    -0.07
    atino
    -0.07
    Loops
    -0.07
     mắt
    -0.07
    gir
    -0.07
     Laugh
    -0.07
     Aud
    -0.07
    POSITIVE LOGITS
     JNICALL
    0.08
     webcam
    0.08
    .geometry
    0.08
     protagonista
    0.07
    -нибудь
    0.07
    宁
    0.07
    :image
    0.07
     JCheck
    0.07
     BAC
    0.07
    ක්ෂ
    0.07
    Activations Density 0.006%

    No Known Activations