© 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. 68871
    Prev
    Next
    INDEX
    Explanations

    needs or could use

    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
    ium
    -0.08
    зь
    -0.08
     obligation
    -0.07
    .as
    -0.07
     obligations
    -0.07
     prompted
    -0.07
    .edit
    -0.07
    .office
    -0.07
    ruž
    -0.07
     Monet
    -0.07
    POSITIVE LOGITS
     �
    0.09
     desperately
    0.09
     enlightenment
    0.08
     Soul
    0.08
     behoefte
    0.08
     necesit
    0.08
    Grand
    0.08
     balm
    0.08
     behöver
    0.08
     needle
    0.08
    Activations Density 0.028%

    No Known Activations