© 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. 77806
    Prev
    Next
    INDEX
    Explanations

    (

    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
     upsetting
    -0.08
     �
    -0.08
     Tenn
    -0.08
    493
    -0.07
    _stride
    -0.07
     demais
    -0.07
     바랍니다
    -0.07
     det
    -0.07
     Stitch
    -0.07
     intensidade
    -0.07
    POSITIVE LOGITS
     lots
    0.08
     CMP
    0.08
     there's
    0.08
     TODO
    0.07
    hle
    0.07
    CMP
    0.07
     something
    0.07
    /h
    0.07
     disclaim
    0.07
     ICS
    0.07
    Activations Density 0.105%

    No Known Activations