© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99159
    Prev
    Next
    INDEX
    Explanations

    1

    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
     Volt
    -0.09
     proposal
    -0.08
     stair
    -0.08
    标题
    -0.08
     शीर्ष
    -0.08
     título
    -0.08
     kuuluu
    -0.07
    urpose
    -0.07
    [T
    -0.07
    Volt
    -0.07
    POSITIVE LOGITS
    /avatar
    0.11
    -avatar
    0.10
     אדם
    0.10
    _gender
    0.09
    .avatar
    0.09
    人物
    0.09
    Avatar
    0.09
     البشرية
    0.09
     mmadụ
    0.09
    .sex
    0.09
    Activations Density 0.011%

    No Known Activations