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. 104244
    Prev
    Next
    INDEX
    Explanations

    name

    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
    Ис
    -0.09
     fyrst
    -0.08
     Stu
    -0.08
    adal
    -0.08
     الاول
    -0.07
     Survey
    -0.07
     Ис
    -0.07
    -Mar
    -0.07
     anne
    -0.07
     الكبير
    -0.07
    POSITIVE LOGITS
    正在
    0.10
    lernen
    0.09
     snapping
    0.09
     inaccuracies
    0.08
     feelings
    0.08
    taxonomy
    0.08
    describe
    0.08
     categorize
    0.08
     aromas
    0.08
     classify
    0.08
    Activations Density 0.013%

    No Known Activations