© 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. 3-RESID-POST-AA
    11. 3042
    Prev
    Next
    INDEX
    Explanations

    باشد

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nut
    -0.09
     Dimit
    -0.08
     nej
    -0.08
     병
    -0.08
    Nut
    -0.08
     والع
    -0.07
     �
    -0.07
     ross
    -0.07
     Occ
    -0.07
     сне
    -0.07
    POSITIVE LOGITS
    වා
    0.08
     sliding
    0.07
     وص
    0.07
     المق
    0.07
     بق
    0.07
     lifted
    0.07
    .Query
    0.07
    lift
    0.07
     ولا
    0.07
     வித
    0.07
    Activations Density 0.001%

    No Known Activations