© 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. 114158
    Prev
    Next
    INDEX
    Explanations

    sqrt

    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
     Probably
    -0.08
     beard
    -0.08
     loaf
    -0.08
     ની
    -0.08
     muffins
    -0.08
     shortage
    -0.08
     bann
    -0.08
     कविता
    -0.08
    _need
    -0.08
     meldt
    -0.08
    POSITIVE LOGITS
    icky
    0.08
     causing
    0.07
    _Request
    0.07
    zie
    0.07
    )^
    0.07
    vs
    0.07
     providing
    0.07
    씩
    0.07
     establishing
    0.07
     �
    0.07
    Activations Density 0.038%

    No Known Activations