© 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. 23-RESID-POST-AA
    6. 49061
    Prev
    Next
    INDEX
    Explanations

    archiv

    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
     uporab
    -0.08
     Punt
    -0.08
    .flight
    -0.08
    asl
    -0.07
     publ
    -0.07
     auditory
    -0.07
     Mb
    -0.07
     М
    -0.07
     žele
    -0.07
     Athletic
    -0.07
    POSITIVE LOGITS
    ner
    0.08
    ၉
    0.08
     victor
    0.08
    istiche
    0.08
    Prefix
    0.08
    Bright
    0.08
    itir
    0.08
    istique
    0.07
    :R
    0.07
    istu
    0.07
    Activations Density 0.000%

    No Known Activations