© 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. 19-RESID-POST-AA
    11. 20504
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ishl
    -0.08
     lógico
    -0.07
     reserved
    -0.07
     Falcon
    -0.07
    REAM
    -0.07
    IMENT
    -0.07
    ಂಡ
    -0.07
    大胆
    -0.07
    imental
    -0.07
     Werke
    -0.07
    POSITIVE LOGITS
    börse
    0.12
    omschrijving
    0.11
    bing
    0.11
    Posting
    0.11
     seekers
    0.11
    -market
    0.11
    portunity
    0.11
    angebot
    0.11
    bers
    0.11
    titel
    0.11
    Activations Density 0.030%

    No Known Activations