© 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. 6585
    Prev
    Next
    INDEX
    Explanations

    to

    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
    ecast
    -0.08
     иҷро
    -0.08
    implementation
    -0.08
     pleno
    -0.08
     méid
    -0.08
     ім
    -0.08
     арен
    -0.07
     genial
    -0.07
    loan
    -0.07
     ක්
    -0.07
    POSITIVE LOGITS
     separated
    0.47
     separar
    0.42
     separados
    0.42
     separates
    0.41
    -separated
    0.40
     sépar
    0.40
     séparation
    0.40
     separating
    0.39
     separación
    0.39
     separation
    0.39
    Activations Density 0.068%

    No Known Activations