© 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 EvalsExportsinterp-engineNEWAPI 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. 111428
    Prev
    Next
    INDEX
    Explanations

    -only

    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
     Rise
    -0.08
     {/*
    -0.08
    Rise
    -0.07
    .Tests
    -0.07
     cust
    -0.07
    gence
    -0.07
    _ud
    -0.07
    ဆ
    -0.07
    ịa
    -0.07
    ೂ
    -0.07
    POSITIVE LOGITS
    -mo
    0.08
    osm
    0.08
     calculates
    0.08
     Rik
    0.07
    イ
    0.07
    膜
    0.07
     Adel
    0.07
     paradise
    0.07
     facto
    0.07
     veneer
    0.07
    Activations Density 0.006%

    No Known Activations