© 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. 1209
    Prev
    Next
    INDEX
    Explanations

    assistant

    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
     Banks
    -0.08
     destruct
    -0.08
     Stone
    -0.07
    �
    -0.07
     tot
    -0.07
     sauces
    -0.07
    Stone
    -0.07
     renovations
    -0.07
     stone
    -0.06
     containers
    -0.06
    POSITIVE LOGITS
     Upt
    0.08
     estando
    0.08
    0.08
     imediato
    0.08
    dv
    0.08
     laden
    0.08
    пр
    0.08
     furry
    0.07
     спраш
    0.07
    خت
    0.07
    Activations Density 0.111%

    No Known Activations