© 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. 29023
    Prev
    Next
    INDEX
    Explanations

    Bulging eyes

    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
     chain
    -0.10
    Chain
    -0.09
    (chain
    -0.08
    .chain
    -0.08
     Chain
    -0.08
    _chain
    -0.08
     leveraging
    -0.07
     chains
    -0.07
     imput
    -0.07
     impress
    -0.07
    POSITIVE LOGITS
     whiten
    0.08
     phối
    0.08
     loosen
    0.08
    orderen
    0.08
     ανάπτυ
    0.08
     eyeb
    0.08
     ikun
    0.08
     macho
    0.08
     huv
    0.08
     zhv
    0.08
    Activations Density 0.006%

    No Known Activations