Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12890
    Prev
    Next
    INDEX
    Explanations

    Fill-in-the-blank tasks

    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
     পৃথ
    -0.08
    rent
    -0.08
     két
    -0.08
    lst
    -0.08
     سهم
    -0.08
    -0.08
    heal
    -0.08
     Rauch
    -0.08
     apuestas
    -0.08
     apuesta
    -0.07
    POSITIVE LOGITS
     ____
    0.08
     treba
    0.08
     sar
    0.08
     schemes
    0.08
     PY
    0.08
    ,%
    0.08
    ایا
    0.07
    pps
    0.07
     inc
    0.07
    でしょう
    0.07
    Activations Density 0.033%

    No Known Activations