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. 11575
    Prev
    Next
    INDEX
    Explanations

    editor

    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
     mattress
    -0.09
     tissu
    -0.08
     kato
    -0.08
     footprint
    -0.08
    asily
    -0.08
    恋
    -0.07
    מח
    -0.07
    .hardware
    -0.07
     atte
    -0.07
     notor
    -0.07
    POSITIVE LOGITS
    (editor
    0.10
     curator
    0.10
    editor
    0.10
    /editor
    0.10
     editorial
    0.09
     editor
    0.09
     curated
    0.09
     anthology
    0.09
    Editing
    0.09
    .Editor
    0.09
    Activations Density 0.047%

    No Known Activations