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. 27336
    Prev
    Next
    INDEX
    Explanations

    numerical calculations

    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
     অভিযান
    -0.10
     relic
    -0.09
     вой
    -0.09
     খবর
    -0.09
    ศก
    -0.09
     قوات
    -0.09
     تصویر
    -0.08
     صلی
    -0.08
     വാർത്ത
    -0.08
     conqu
    -0.08
    POSITIVE LOGITS
     float
    0.10
    _float
    0.10
    <float
    0.10
    (float
    0.09
    _precision
    0.09
     GLfloat
    0.09
     decimal
    0.09
     pod
    0.09
     {:.
    0.09
    float
    0.09
    Activations Density 0.166%

    No Known Activations