© 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. 50334
    Prev
    Next
    INDEX
    Explanations

    Russian text

    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
    jí
    -0.08
     Fundamental
    -0.07
    (blob
    -0.07
    	std
    -0.07
     Alter
    -0.07
     定
    -0.07
     npc
    -0.07
    (static
    -0.07
     fondamentale
    -0.07
    -0.07
    POSITIVE LOGITS
    устить
    0.21
    уска
    0.21
    уск
    0.17
    уст
    0.16
    ущ
    0.16
    ус
    0.15
    у
    0.11
    адает
    0.10
    усь
    0.10
    usc
    0.09
    Activations Density 0.001%
    No Known Activations