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. 112891
    Prev
    Next
    INDEX
    Explanations

    finger

    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
     Malta
    -0.08
     rainforest
    -0.08
    achement
    -0.08
    achel
    -0.07
     Heavenly
    -0.07
     Fringe
    -0.07
    imetype
    -0.07
     yearly
    -0.07
    当地
    -0.07
     hurricane
    -0.07
    POSITIVE LOGITS
     đỏ
    0.09
     eyebrows
    0.09
     phát
    0.08
     satt
    0.08
     brothers
    0.08
     muhimu
    0.08
     sanya
    0.08
     phẩm
    0.08
    แดง
    0.08
     knees
    0.08
    Activations Density 0.002%

    No Known Activations