© 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. 25858
    Prev
    Next
    INDEX
    Explanations

    acid

    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
     Teacher
    -0.08
     apan
    -0.07
     гум
    -0.07
     humanities
    -0.07
    unahing
    -0.07
     محور
    -0.07
    突然
    -0.07
     ಮುಖ
    -0.07
     yhd
    -0.07
     exceptions
    -0.07
    POSITIVE LOGITS
    ıdır
    0.08
    amac
    0.07
     supplying
    0.07
    참
    0.07
    ę
    0.07
    ?t
    0.07
     uporabo
    0.07
    ęt
    0.07
    'all
    0.07
    áculos
    0.07
    Activations Density 0.000%

    No Known Activations