© 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. 13353
    Prev
    Next
    INDEX
    Explanations

    programming tasks

    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
     sério
    -0.07
    Weiter
    -0.07
     adicionais
    -0.07
    abu
    -0.07
     zna
    -0.07
     nett
    -0.07
     spat
    -0.07
     Weiter
    -0.07
    Separ
    -0.07
    部分
    -0.06
    POSITIVE LOGITS
     nang
    0.09
     tup
    0.08
    0.08
    ismod
    0.08
     Gob
    0.07
    opi
    0.07
    -Pl
    0.07
    يي
    0.07
     Almond
    0.07
    จำ
    0.07
    Activations Density 0.000%
    No Known Activations