© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 49719
    Prev
    Next
    INDEX
    Explanations

    tend

    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
     Sandra
    -0.10
    .rar
    -0.08
     mines
    -0.08
    么
    -0.08
    ulan
    -0.08
    ắm
    -0.08
    Sandra
    -0.08
     semiconductor
    -0.08
    ademic
    -0.08
    alous
    -0.08
    POSITIVE LOGITS
    ક્ર
    0.08
     motion
    0.07
     reused
    0.07
    B
    0.07
     ripped
    0.07
     inok
    0.07
    ক্র
    0.07
    .motion
    0.07
     futuros
    0.07
     incorporated
    0.07
    Activations Density 0.002%

    No Known Activations