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. 65435
    Prev
    Next
    INDEX
    Explanations

    separators

    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
    ვნის
    -0.09
    。那么
    -0.09
    ორის
    -0.09
    —the
    -0.09
     sbobet
    -0.08
    ,那么
    -0.08
    -ერთ
    -0.08
    ത്തില
    -0.08
     حصول
    -0.08
     harness
    -0.08
    POSITIVE LOGITS
     approx
    0.10
     ggf
    0.09
     thru
    0.08
    =>
    0.08
     beware
    0.08
    (()=>{↵
    0.08
    ⇒
    0.08
    ()=>
    0.08
    .table
    0.08
     pág
    0.08
    Activations Density 0.731%

    No Known Activations