© 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. 50893
    Prev
    Next
    INDEX
    Explanations

    literature in different languages

    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
    caller
    -0.09
    Tooltip
    -0.08
     Caller
    -0.08
     prized
    -0.08
    竞技
    -0.08
    Across
    -0.07
    trigger
    -0.07
     聚
    -0.07
     caller
    -0.07
    Trigger
    -0.07
    POSITIVE LOGITS
     literature
    0.24
     Literature
    0.24
     Literatur
    0.20
     littérature
    0.20
     ಸಾಹಿತ್ಯ
    0.20
    Liter
    0.19
     সাহিত্য
    0.19
     literatura
    0.19
     литера
    0.19
     әдеби
    0.18
    Activations Density 0.046%

    No Known Activations