© 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. 114156
    Prev
    Next
    INDEX
    Explanations

    third

    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
    .b
    -0.08
     container
    -0.07
    Tab
    -0.07
     nim
    -0.07
     press
    -0.07
     survivors
    -0.07
    [A
    -0.07
     stable
    -0.07
     or
    -0.07
     Minis
    -0.06
    POSITIVE LOGITS
     apl
    0.09
    -third
    0.08
     ভাগ
    0.08
    -thirds
    0.08
    agé
    0.08
    奋
    0.08
    gebied
    0.08
    -finals
    0.08
     gete
    0.08
     Ό
    0.08
    Activations Density 0.005%

    No Known Activations