© 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. 50104
    Prev
    Next
    INDEX
    Explanations

    bit

    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
    'accueil
    -0.08
     сез
    -0.08
    ظم
    -0.08
     skipped
    -0.07
    ONEY
    -0.07
     toucher
    -0.07
    UFACTUR
    -0.07
     ọgwụ
    -0.07
    _BOOK
    -0.07
     چه
    -0.07
    POSITIVE LOGITS
    fields
    0.13
    terness
    0.13
    mapped
    0.12
    uminous
    0.12
    shift
    0.12
    wise
    0.12
    maps
    0.11
    luni
    0.11
    depth
    0.11
    bucket
    0.11
    Activations Density 0.009%

    No Known Activations