© 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. 96367
    Prev
    Next
    INDEX
    Explanations

    pro

    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
     Gram
    -0.08
     prou
    -0.08
    ore
    -0.08
    te
    -0.07
     geloven
    -0.07
     goede
    -0.07
    ğine
    -0.07
     biodegradable
    -0.07
     gründ
    -0.07
    rekken
    -0.07
    POSITIVE LOGITS
    stitution
    0.12
    STITUTE
    0.11
    stitute
    0.10
    STIT
    0.10
    stitut
    0.10
    creative
    0.10
    stit
    0.09
     creatieve
    0.09
     kreative
    0.08
     kreat
    0.08
    Activations Density 0.001%

    No Known Activations