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. 30322
    Prev
    Next
    INDEX
    Explanations

    encyclopedias

    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
    thorne
    -0.08
     stronger
    -0.08
     Tanner
    -0.07
    סר
    -0.07
    مع
    -0.07
    いる
    -0.07
     venc
    -0.07
    -0.07
     മേ
    -0.07
     prescription
    -0.07
    POSITIVE LOGITS
     Britannica
    0.13
     encyclopedia
    0.13
     encycl
    0.12
    百科
    0.12
     Encyclopedia
    0.11
     Encycl
    0.10
    .Entry
    0.09
    opedia
    0.09
     IDictionary
    0.08
    икип
    0.08
    Activations Density 0.008%

    No Known Activations