Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 60184
    Prev
    Next
    INDEX
    Explanations

    Math word problems

    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
    embr
    -0.08
     Sons
    -0.08
    -0.07
    ्या
    -0.07
    trat
    -0.07
    pendicular
    -0.07
     이후
    -0.07
     文
    -0.07
     guardian
    -0.07
    徐
    -0.07
    POSITIVE LOGITS
    _needed
    0.09
    \Schema
    0.08
    Needed
    0.08
     масс
    0.08
     purchased
    0.08
     שהיא
    0.08
     slurry
    0.08
     regi
    0.07
     tham
    0.07
     masse
    0.07
    Activations Density 0.049%

    No Known Activations