© 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 EvalsExportsinterp-engineNEWAPI 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. 50974
    Prev
    Next
    INDEX
    Explanations

    sculpture

    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
    ্স
    -0.08
    Milliseconds
    -0.08
     একটি
    -0.08
     যৌ
    -0.07
    ুস
    -0.07
     সত
    -0.07
     lefel
    -0.07
    s
    -0.07
    isil
    -0.07
     osu
    -0.07
    POSITIVE LOGITS
     sculpture
    0.18
     sculptures
    0.15
    雕
    0.14
     statue
    0.13
    culpt
    0.13
     escult
    0.13
     statues
    0.12
     Sculpture
    0.12
     искусства
    0.12
     sculpt
    0.12
    Activations Density 0.008%

    No Known Activations