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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48465
    Prev
    Next
    INDEX
    Explanations

    period

    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
    -unit
    -0.08
     Luxus
    -0.08
     clad
    -0.08
     Unidade
    -0.08
     eto
    -0.08
    ידן
    -0.08
     Valores
    -0.08
     synonymous
    -0.08
     norme
    -0.08
     Educação
    -0.08
    POSITIVE LOGITS
    akap
    0.08
    asem
    0.08
    ston
    0.07
     stakeholder
    0.07
    ows
    0.07
    urrection
    0.07
     dispers
    0.07
    mooth
    0.07
    Inspect
    0.07
    essions
    0.07
    Activations Density 0.000%

    No Known Activations