© 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. 23-RESID-POST-AA
    6. 96972
    Prev
    Next
    INDEX
    Explanations

    ###

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?
    -0.12
    11
    -0.11
    "?
    -0.11
    90
    -0.11
    9
    -0.11
    81
    -0.11
    "",
    -0.11
    $\
    -0.11
    ?,
    -0.11
    This
    -0.11
    POSITIVE LOGITS
     Sidebar
    0.11
     多宝
    0.10
     Passive
    0.10
     靖
    0.10
     Responsable
    0.10
     ა
    0.10
     Daten
    0.10
     示例
    0.10
     蓝盾
    0.10
     Advantages
    0.10
    Activations Density 0.022%

    No Known Activations