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. 111944
    Prev
    Next
    INDEX
    Explanations

    Math and directions

    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
     interception
    -0.07
    &t
    -0.07
     eriti
    -0.07
    ぶ
    -0.07
     तरीका
    -0.07
    -0.07
    游戏下载
    -0.07
     clickable
    -0.07
     guy
    -0.07
     dropdown
    -0.07
    POSITIVE LOGITS
     cancel
    0.12
     canc
    0.12
    cancel
    0.11
    Cancel
    0.11
     компен
    0.11
     cancelling
    0.11
     Cancel
    0.11
    .cancel
    0.11
    (cancel
    0.10
    balances
    0.10
    Activations Density 0.120%

    No Known Activations