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. 15-RESID-POST-AA
    6. 18923
    Prev
    Next
    INDEX
    Explanations

    Title tags and title content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     embol
    -0.08
    _RX
    -0.08
     caffeine
    -0.08
    partition
    -0.08
     jogador
    -0.08
     plays
    -0.07
    不了
    -0.07
    較
    -0.07
     solvent
    -0.07
     prey
    -0.07
    POSITIVE LOGITS
    欢迎
    0.12
     제목
    0.12
    Welcome
    0.12
    <title
    0.12
    标题
    0.12
     शीर्ष
    0.12
    タイトル
    0.12
     Welcome
    0.11
    Titel
    0.11
     Titel
    0.11
    Activations Density 0.003%

    No Known Activations