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. 119256
    Prev
    Next
    INDEX
    Explanations

    .append

    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
    /repos
    -0.09
    /br
    -0.08
    -лет
    -0.08
    wreck
    -0.08
    spawn
    -0.08
    Atual
    -0.08
     epidem
    -0.08
    /sw
    -0.08
    .Expr
    -0.08
    enschappelijke
    -0.08
    POSITIVE LOGITS
     urlencode
    0.09
    Pon
    0.09
     banana
    0.09
     username
    0.08
    ーバ
    0.08
     enctype
    0.08
     textarea
    0.08
     Banana
    0.08
     dried
    0.08
     csrf
    0.08
    Activations Density 0.004%

    No Known Activations