© 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. 68341
    Prev
    Next
    INDEX
    Explanations

    mathematics equations

    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
     interpersonal
    -0.08
     werkzaamheden
    -0.08
    (correct
    -0.08
    dod
    -0.08
     assumptions
    -0.07
    兼职
    -0.07
    Х
    -0.07
    .Contract
    -0.07
     wording
    -0.07
     dod
    -0.07
    POSITIVE LOGITS
    balanced
    0.09
    Balanced
    0.09
     balanced
    0.08
    ubic
    0.08
     ovan
    0.08
     alvo
    0.08
    ober
    0.08
     équilibr
    0.08
     ober
    0.08
    平方
    0.08
    Activations Density 0.060%

    No Known Activations