© 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. 50416
    Prev
    Next
    INDEX
    Explanations

    вку

    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
    j
    -0.08
    žni
    -0.08
    jati
    -0.08
    igg
    -0.07
    ılı
    -0.07
    級
    -0.07
    æg
    -0.07
    gesi
    -0.07
    g
    -0.07
    jén
    -0.07
    POSITIVE LOGITS
    сов
    0.11
    са
    0.10
    ло
    0.09
    šení
    0.09
    یدہ
    0.09
    шая
    0.09
    .coroutines
    0.09
    омин
    0.08
    су
    0.08
    ание
    0.08
    Activations Density 0.001%

    No Known Activations