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

    Neuronpedia

    Jacobian LensNEW
    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. 23-RESID-POST-AA
    11. 50017
    Prev
    Next
    INDEX
    Explanations

    federal or state

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enero
    -0.12
     janeiro
    -0.11
     İran
    -0.11
     제주
    -0.10
     ایران
    -0.10
     janvier
    -0.10
     韩国
    -0.10
     魔兽
    -0.10
     安徽
    -0.09
     金叶
    -0.09
    POSITIVE LOGITS
     Property
    0.10
     Council
    0.09
    নি
    0.09
    nym
    0.09
     property
    0.09
    ne
    0.08
    ness
    0.08
     properties
    0.08
    uary
    0.08
    leet
    0.08
    Activations Density 0.010%

    No Known Activations