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. 130817
    Prev
    Next
    INDEX
    Explanations

    ending fragments with "ri" followed by "pe"

    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
     Аммо
    -0.09
    एको
    -0.09
    ்கள்
    -0.08
    న్
    -0.08
    ंच
    -0.08
    مىز
    -0.08
     grouped
    -0.08
    రు
    -0.08
     אבל
    -0.07
    πουργ
    -0.07
    POSITIVE LOGITS
    quette
    0.11
    qull
    0.11
    quets
    0.11
    huana
    0.11
    quettes
    0.10
    quec
    0.10
    quando
    0.10
    queline
    0.10
    um
    0.10
    quetas
    0.10
    Activations Density 0.027%

    No Known Activations