© 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. 13019
    Prev
    Next
    INDEX
    Explanations

    tipo

    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
     velvet
    -0.08
     Reflect
    -0.08
    ביל
    -0.08
    Reflect
    -0.08
     Wichita
    -0.08
     ciência
    -0.08
    arante
    -0.08
    veli
    -0.08
    vā
    -0.08
    puru
    -0.07
    POSITIVE LOGITS
    .backward
    0.07
     strains
    0.07
    lost
    0.07
    ‘‘
    0.07
     
    0.07
     ye
    0.07
     Gordon
    0.07
     zum
    0.07
     halluc
    0.07
     danış
    0.07
    Activations Density 0.009%

    No Known Activations