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. 88007
    Prev
    Next
    INDEX
    Explanations

    operations on 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
     پیش
    -0.09
    alat
    -0.08
     स्कूल
    -0.07
     póź
    -0.07
     towering
    -0.07
    .pred
    -0.07
     stalking
    -0.07
    -0.07
    (video
    -0.07
     سفر
    -0.07
    POSITIVE LOGITS
     affected
    0.09
     simultaneously
    0.09
    -Owned
    0.09
    _Update
    0.09
     afflicted
    0.09
    -owned
    0.08
    ffected
    0.08
     bens
    0.08
     одновременно
    0.08
    UPDATE
    0.08
    Activations Density 0.033%

    No Known Activations