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. 53004
    Prev
    Next
    INDEX
    Explanations

    star

    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
    ields
    -0.08
    uvos
    -0.07
     مؤ
    -0.07
     quil
    -0.07
     afgest
    -0.07
     lighter
    -0.07
     latt
    -0.07
     bolje
    -0.07
     landscapes
    -0.07
    .ylabel
    -0.07
    POSITIVE LOGITS
     centralized
    0.12
     hub
    0.12
     केंद
    0.12
     hubs
    0.11
     pusat
    0.11
     central
    0.11
     কেন্দ্র
    0.10
    central
    0.10
    hub
    0.10
     중심
    0.10
    Activations Density 0.015%

    No Known Activations