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. 45058
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     persona
    -0.08
     வே
    -0.08
    valor
    -0.08
     airt
    -0.07
     timezone
    -0.07
    persona
    -0.07
    Persona
    -0.07
     યુ
    -0.07
     ""↵↵
    -0.07
     Deo
    -0.07
    POSITIVE LOGITS
     dozen
    0.09
     waving
    0.09
     fewer
    0.09
    颗
    0.09
     تعداد
    0.09
    _COUNT
    0.08
     എണ്ണം
    0.08
    (count
    0.08
    ,count
    0.08
    $count
    0.08
    Activations Density 0.035%

    No Known Activations