© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68699
    Prev
    Next
    INDEX
    Explanations

    Computer memory management

    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
     качества
    -0.08
    _again
    -0.07
    _title
    -0.07
     Nant
    -0.07
    _lt
    -0.07
     кач
    -0.07
     bedanken
    -0.07
    匙
    -0.07
    _examples
    -0.07
     negotiation
    -0.07
    POSITIVE LOGITS
     contiguous
    0.11
    packed
    0.11
     packed
    0.10
     storing
    0.10
    Stored
    0.10
     Packed
    0.09
    存
    0.09
     stored
    0.09
    indexed
    0.09
     march
    0.09
    Activations Density 0.004%

    No Known Activations