© 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. 13158
    Prev
    Next
    INDEX
    Explanations

    hat

    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
     schwer
    -0.08
     enfermedad
    -0.08
     Samen
    -0.08
     Lopez
    -0.08
     Alonso
    -0.07
    जह
    -0.07
    well
    -0.07
     suerte
    -0.07
     Opinion
    -0.07
     enzyme
    -0.07
    POSITIVE LOGITS
    руж
    0.09
    (delegate
    0.08
     dispers
    0.08
     ауд
    0.08
     dispon
    0.08
     еще
    0.07
    েই
    0.07
     doute
    0.07
    祝い
    0.07
    త్స
    0.07
    Activations Density 0.000%

    No Known Activations