© 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. 3164
    Prev
    Next
    INDEX
    Explanations

    /pro

    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
    эг
    -0.07
     lernen
    -0.07
    لار
    -0.07
     شتون
    -0.07
     mono
    -0.07
     lisboa
    -0.07
    (nn
    -0.07
     ಘ
    -0.07
     verble
    -0.07
    桂
    -0.07
    POSITIVE LOGITS
     feiten
    0.08
     propone
    0.08
     Nee
    0.08
     NJ
    0.08
     ebb
    0.08
    +y
    0.07
    oraj
    0.07
     awarding
    0.07
    atii
    0.07
     Dian
    0.07
    Activations Density 0.000%

    No Known Activations