© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7906
    Prev
    Next
    INDEX
    Explanations

    Mathematical examples

    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
    ນ
    -0.08
    ودية
    -0.08
    ટી
    -0.07
    ་
    -0.07
    Creative
    -0.07
     Creative
    -0.07
    цеп
    -0.07
     исполн
    -0.07
     �
    -0.07
     ಅ
    -0.07
    POSITIVE LOGITS
    xo
    0.08
    eping
    0.08
     geval
    0.07
     Xa
    0.07
    vr
    0.07
    fight
    0.07
     sori
    0.07
    better
    0.07
    _matrix
    0.07
    orbit
    0.07
    Activations Density 0.000%

    No Known Activations