© 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. 110674
    Prev
    Next
    INDEX
    Explanations

    to

    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
     metá
    -0.08
    IFE
    -0.08
    <TResult
    -0.07
    Consent
    -0.07
     ಘಟ
    -0.07
    ৎস
    -0.07
    Invert
    -0.07
    reinterpret
    -0.07
    Exec
    -0.07
    ক্ষ
    -0.07
    POSITIVE LOGITS
     adjacency
    0.13
     neighbors
    0.12
     adjacent
    0.11
    邻
    0.10
     voisins
    0.10
     neigh
    0.10
    _neighbors
    0.10
    neighbors
    0.09
    Adjacent
    0.09
     сосед
    0.09
    Activations Density 0.022%

    No Known Activations