© 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. 11-RESID-POST-AA
    6. 29038
    Prev
    Next
    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     supposedly
    -0.08
    parm
    -0.07
    -0.07
     väär
    -0.07
     Joachim
    -0.07
    组成
    -0.07
    illus
    -0.07
    firm
    -0.07
     lor
    -0.07
    .DE
    -0.07
    POSITIVE LOGITS
     mere
    0.09
     ally
    0.09
     sparkle
    0.08
     Ci
    0.08
     Ally
    0.07
     скорее
    0.07
     mı
    0.07
     smiles
    0.07
     Parkway
    0.07
     sourire
    0.07
    Activations Density 0.021%

    No Known Activations