© 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. 30423
    Prev
    Next
    INDEX
    Explanations

    wait for drying

    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
     отношения
    -0.08
     ради
    -0.08
     таким
    -0.08
     राश
    -0.08
     Beziehung
    -0.08
     без
    -0.08
     Bertrand
    -0.07
     الفوز
    -0.07
     فایل
    -0.07
     необ
    -0.07
    POSITIVE LOGITS
     drying
    0.12
     dries
    0.10
     demora
    0.09
    等待
    0.09
     soaking
    0.09
     vaxt
    0.09
     শুক
    0.09
     기다
    0.08
    .wait
    0.08
     staining
    0.08
    Activations Density 0.026%

    No Known Activations