© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 3054
    Prev
    Next
    INDEX
    Explanations

    ának

    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
     наше
    -0.08
     сделал
    -0.08
     леп
    -0.07
     authenticated
    -0.07
     Madeira
    -0.07
     urls
    -0.07
    authenticated
    -0.07
    hao
    -0.07
     merke
    -0.07
     homme
    -0.07
    POSITIVE LOGITS
     Twilight
    0.08
    ைக்க
    0.08
     Tarn
    0.08
     pung
    0.08
     suf
    0.08
    െയ
    0.08
     piemē
    0.07
     palīdz
    0.07
     अफ
    0.07
    ainter
    0.07
    Activations Density 0.000%

    No Known Activations