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. 98595
    Prev
    Next
    INDEX
    Explanations

    Another language (possibly Lithuanian)

    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
     mornings
    -0.08
    ធ
    -0.08
     salida
    -0.08
    Morning
    -0.08
    IFIER
    -0.08
    予定
    -0.08
    .ALL
    -0.07
     novia
    -0.07
     entènèt
    -0.07
    ાળા
    -0.07
    POSITIVE LOGITS
    age
    0.10
    par
    0.09
    agnet
    0.09
    akom
    0.09
    atto
    0.09
    agn
    0.09
    paring
    0.09
    agen
    0.09
    aking
    0.08
    ages
    0.08
    Activations Density 0.001%

    No Known Activations