© 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. 992
    Prev
    Next
    INDEX
    Explanations

    API

    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
     urgently
    -0.09
     रह
    -0.08
    raud
    -0.08
     sobe
    -0.08
     ಗ್ರ
    -0.08
    เ�
    -0.08
    直播
    -0.08
     remix
    -0.08
    Drama
    -0.07
     Drama
    -0.07
    POSITIVE LOGITS
     cylindrical
    0.08
     Kat
    0.07
     Cyl
    0.07
     cartoons
    0.07
     Hungarian
    0.07
     المط
    0.07
    _micro
    0.07
     Tan
    0.07
     tires
    0.07
     dessins
    0.07
    Activations Density 0.005%

    No Known Activations