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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 131026
    Prev
    Next
    INDEX
    Explanations

    G

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     qm
    -0.08
    ении
    -0.08
    লার
    -0.07
    .ht
    -0.07
    .transforms
    -0.07
    llun
    -0.07
    уть
    -0.07
    iddy
    -0.07
    ادر
    -0.07
    ermain
    -0.07
    POSITIVE LOGITS
     Fly
    0.09
    Fly
    0.09
    fly
    0.09
     fly
    0.09
    Region
    0.08
    amt
    0.08
     yax
    0.08
    Dire
    0.08
    уляр
    0.08
    -region
    0.08
    Activations Density 0.000%

    No Known Activations