© 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. 23-RESID-POST-AA
    11. 47916
    Prev
    Next
    INDEX
    Explanations

    proc

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beantwoorden
    -0.09
     precisava
    -0.08
    blo
    -0.08
     Separ
    -0.08
     séparation
    -0.08
    ICK
    -0.08
     separation
    -0.07
     separación
    -0.07
    /modal
    -0.07
    ಿಕ್ಕ
    -0.07
    POSITIVE LOGITS
    urement
    0.16
    urem
    0.10
    UREMENT
    0.10
    umenten
    0.09
    cter
    0.08
    ureen
    0.08
    ensation
    0.08
    Unary
    0.08
    умент
    0.08
     düş
    0.08
    Activations Density 0.001%

    No Known Activations