© 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. 3-RESID-POST-AA
    11. 3136
    Prev
    Next
    INDEX
    Explanations

    color codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     erect
    -0.08
    电话
    -0.08
     vaginal
    -0.07
     Veröffentlich
    -0.07
     acronym
    -0.07
    _WEB
    -0.07
    λόγ
    -0.07
    irr
    -0.07
    _Fe
    -0.07
    Glue
    -0.07
    POSITIVE LOGITS
     Williams
    0.09
    728
    0.09
     товари
    0.08
    857
    0.08
     itens
    0.08
    856
    0.08
     Lenovo
    0.07
     Petit
    0.07
     koi
    0.07
    993
    0.07
    Activations Density 0.016%

    No Known Activations