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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78888
    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
    FLAGS
    -0.08
     invasion
    -0.08
    fangen
    -0.07
     выхода
    -0.07
     infestation
    -0.07
     extravagant
    -0.07
     الحصول
    -0.07
     custody
    -0.07
     adul
    -0.07
     gql
    -0.07
    POSITIVE LOGITS
    Arial
    0.12
     Arial
    0.11
    (Edit
    0.10
     chopped
    0.10
     diced
    0.09
     serif
    0.09
    _Edit
    0.09
    Calibri
    0.09
    /Edit
    0.09
    Editable
    0.09
    Activations Density 0.005%

    No Known Activations