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. 27291
    Prev
    Next
    INDEX
    Explanations

    sync

    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
    wissen
    -0.08
     jeden
    -0.08
    英国
    -0.07
    贝
    -0.07
    മേ
    -0.07
    途中
    -0.07
    તીય
    -0.07
    રિક
    -0.07
     Gilbert
    -0.07
    erschap
    -0.07
    POSITIVE LOGITS
    กับ
    0.09
     contigo
    0.08
    олн
    0.07
     closely
    0.07
    -sama
    0.07
    affold
    0.07
    (lock
    0.07
     sincron
    0.07
     montage
    0.07
    ировка
    0.07
    Activations Density 0.009%

    No Known Activations