© 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. 11-RESID-POST-AA
    11. 44587
    Prev
    Next
    INDEX
    Explanations

    the

    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
     rafting
    -0.10
     terrain
    -0.08
    RIES
    -0.08
    anning
    -0.08
     الإعلان
    -0.08
     जाह
    -0.08
     couvre
    -0.08
    ுந்த
    -0.07
     каш
    -0.07
     memcpy
    -0.07
    POSITIVE LOGITS
    .swap
    0.08
     Convertible
    0.08
     hjelp
    0.08
    ১০
    0.08
     দেশের
    0.08
     consejos
    0.08
     দেশ
    0.08
     significantly
    0.08
     তথ
    0.08
     sulfur
    0.08
    Activations Density 0.013%

    No Known Activations