© 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 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. 113107
    Prev
    Next
    INDEX
    Explanations

    iline

    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
    沉
    -0.08
    949
    -0.07
    娘
    -0.07
     cybers
    -0.07
     stu
    -0.07
     ban
    -0.07
     dép
    -0.07
    948
    -0.07
     cadastr
    -0.07
    ursus
    -0.07
    POSITIVE LOGITS
    Pressure
    0.08
     propon
    0.08
    _pressure
    0.08
     Pressure
    0.08
    .jetbrains
    0.07
     ensayo
    0.07
    estock
    0.07
    pipe
    0.07
    pressure
    0.07
    వి
    0.07
    Activations Density 0.001%

    No Known Activations