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. 131009
    Prev
    Next
    INDEX
    Explanations

    Other language

    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
     عط
    -0.08
    mdi
    -0.07
    Img
    -0.07
     Ikea
    -0.07
     chịu
    -0.07
    ществ
    -0.07
     taba
    -0.07
     Mule
    -0.07
     Sandbox
    -0.07
    imme
    -0.07
    POSITIVE LOGITS
    undet
    0.10
    ilen
    0.10
    ølge
    0.09
    amse
    0.09
    øl
    0.08
    landet
    0.08
    okens
    0.08
    ærer
    0.08
    Entrance
    0.08
    landing
    0.08
    Activations Density 0.000%

    No Known Activations