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. 11-RESID-POST-AA
    6. 75979
    Prev
    Next
    INDEX
    Explanations

    @

    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
    Deux
    -0.08
     machin
    -0.08
     adam
    -0.08
    deith
    -0.08
     دی
    -0.08
    OLF
    -0.08
    纯
    -0.08
     tire
    -0.08
    ملت
    -0.08
    ografía
    -0.07
    POSITIVE LOGITS
     <!
    0.08
     cru
    0.07
     =
    0.07
     Goodman
    0.07
     upe
    0.07
     temática
    0.07
     đặt
    0.07
     POSITION
    0.07
     überhaupt
    0.07
     emin
    0.07
    Activations Density 0.001%

    No Known Activations