© 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. 11-RESID-POST-AA
    11. 26385
    Prev
    Next
    INDEX
    Explanations

    Perlin noise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gré
    -0.08
     IRA
    -0.08
     개최
    -0.07
    Bath
    -0.07
     Cymru
    -0.07
     Paral
    -0.07
     Ou
    -0.07
     આય
    -0.07
     precios
    -0.07
     kpọ
    -0.07
    POSITIVE LOGITS
    atz
    0.09
     hoch
    0.09
     sicher
    0.08
     Robbins
    0.08
    фика
    0.08
    .fn
    0.08
    521
    0.08
    603
    0.08
    265
    0.08
    460
    0.08
    Activations Density 0.001%

    No Known Activations