© 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. 129268
    Prev
    Next
    INDEX
    Explanations

    errors in statements

    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
     sosai
    -0.09
     jantar
    -0.08
     والعمل
    -0.08
     deta
    -0.08
     tabb
    -0.08
     החר
    -0.08
     JNICALL
    -0.08
     отношений
    -0.08
     લઈને
    -0.08
     Wage
    -0.08
    POSITIVE LOGITS
     mistakes
    0.14
     typo
    0.14
     confusing
    0.13
     misunderstanding
    0.13
     ভুল
    0.13
     confusion
    0.13
    Incorrect
    0.12
     misunderstood
    0.12
     mis
    0.12
     misst
    0.12
    Activations Density 0.035%

    No Known Activations