© 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. 23-RESID-POST-AA
    11. 5592
    Prev
    Next
    INDEX
    Explanations

    code instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trend
    -0.08
     Ab
    -0.08
     schedule
    -0.08
     ab
    -0.07
    'ab
    -0.07
    Ab
    -0.07
     AB
    -0.07
     rann
    -0.07
    schedule
    -0.07
    路线
    -0.07
    POSITIVE LOGITS
     부모
    0.09
    pc
    0.09
    129
    0.09
     סמ
    0.08
    PC
    0.08
    pct
    0.08
    actéristiques
    0.07
     pc
    0.07
    ETING
    0.07
    ski
    0.07
    Activations Density 0.000%

    No Known Activations