© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 112663
    Prev
    Next
    INDEX
    Explanations

    common words

    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
    ubere
    -0.08
     ا
    -0.08
     derive
    -0.08
     싶은
    -0.08
     लगा
    -0.08
     morals
    -0.07
    -equiv
    -0.07
    -minded
    -0.07
    ข้อ
    -0.07
    บาท
    -0.07
    POSITIVE LOGITS
     flo
    0.10
     Maintenance
    0.08
    _en
    0.07
    loha
    0.07
     Oficina
    0.07
     Ante
    0.07
    Maintenance
    0.07
     Bremen
    0.07
     магаз
    0.07
    _sh
    0.07
    Activations Density 0.002%

    No Known Activations