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. 43020
    Prev
    Next
    INDEX
    Explanations

    article metadata

    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
     tweaks
    -0.09
    裕
    -0.08
    技巧
    -0.08
     backed
    -0.08
    :↵
    -0.08
     edits
    -0.08
     سپ
    -0.08
     зав
    -0.07
    .practice
    -0.07
     bully
    -0.07
    POSITIVE LOGITS
     Metadata
    0.09
     metadata
    0.09
     TIC
    0.09
     remotely
    0.09
     DTSTART
    0.08
    Ontology
    0.08
    .Metadata
    0.08
     ontology
    0.08
    Metadata
    0.08
    _metadata
    0.08
    Activations Density 0.130%

    No Known Activations