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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 54287
    Prev
    Next
    INDEX
    Explanations

    combinatorics

    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
     Aquarius
    -0.08
    ПО
    -0.08
    woofer
    -0.08
    то
    -0.08
    buyer
    -0.08
    ondas
    -0.07
    yet
    -0.07
     androgen
    -0.07
     afge
    -0.07
    Nathan
    -0.07
    POSITIVE LOGITS
     combin
    0.10
    /stat
    0.10
     counting
    0.08
     enumer
    0.08
     giveaways
    0.08
    .Concurrent
    0.08
     nuggets
    0.08
    /count
    0.07
    统计
    0.07
     zählt
    0.07
    Activations Density 0.005%

    No Known Activations