© 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. 929
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    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
    ాంటి
    -0.08
     পর
    -0.08
    ান্ত
    -0.08
    IDADE
    -0.08
     comprov
    -0.07
     định
    -0.07
    inian
    -0.07
     GTX
    -0.07
    রি
    -0.07
     frat
    -0.07
    POSITIVE LOGITS
    づ
    0.09
    施設
    0.07
     mound
    0.07
     ers
    0.07
     उत
    0.07
    iza
    0.07
     பொ
    0.07
     sponge
    0.07
     آلات
    0.07
     ti
    0.07
    Activations Density 0.001%

    No Known Activations