© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2869
    Prev
    Next
    INDEX
    Explanations

    of

    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
    高速
    -0.09
     comic
    -0.08
    転
    -0.08
     faste
    -0.08
    Compet
    -0.08
    客服
    -0.07
    �
    -0.07
    漫画
    -0.07
     sharpen
    -0.07
    Cart
    -0.07
    POSITIVE LOGITS
    0.09
     umbre
    0.08
     Mittel
    0.08
     Based
    0.08
     midd
    0.08
    alas
    0.07
     erstellt
    0.07
     candle
    0.07
    Quiet
    0.07
     Quiet
    0.07
    Activations Density 0.000%

    No Known Activations