© 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. 110632
    Prev
    Next
    INDEX
    Explanations

    spiral

    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
    .dimension
    -0.09
     consolidation
    -0.08
    moor
    -0.08
    öp
    -0.08
     reimburse
    -0.08
     commenting
    -0.08
     Consolid
    -0.08
    ökk
    -0.08
    ��
    -0.08
     concurrence
    -0.07
    POSITIVE LOGITS
     vibrant
    0.09
     ornate
    0.08
     rotor
    0.08
     spiral
    0.08
     periodic
    0.08
     icy
    0.08
     stained
    0.08
    موع
    0.08
     güzel
    0.08
    道路
    0.07
    Activations Density 0.001%

    No Known Activations