© 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. 7-RESID-POST-AA
    11. 1337
    Prev
    Next
    INDEX
    Explanations

    private

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Announcements
    -0.09
    ители
    -0.08
    △
    -0.08
     overl
    -0.08
     impart
    -0.07
     inaugur
    -0.07
     Delhi
    -0.07
    Delhi
    -0.07
    Income
    -0.07
     Dresden
    -0.07
    POSITIVE LOGITS
     Miley
    0.08
     Roz
    0.08
     στά
    0.08
    (Intent
    0.08
     Ray
    0.07
     Fier
    0.07
    털
    0.07
     Ef
    0.07
     roz
    0.07
     Regular
    0.07
    Activations Density 0.002%

    No Known Activations