© 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. 50713
    Prev
    Next
    INDEX
    Explanations

    ез

    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
    éid
    -0.08
    aka
    -0.08
     τις
    -0.07
     کیوں
    -0.07
    স্থ
    -0.07
    σι
    -0.07
    ொ
    -0.07
    back
    -0.07
     deras
    -0.07
    ("""↵
    -0.07
    POSITIVE LOGITS
     accur
    0.09
     achten
    0.08
     accuracy
    0.07
    оруж
    0.07
    achelorette
    0.07
     ader
    0.07
    амп
    0.07
     jongen
    0.07
    zub
    0.07
     dikkat
    0.07
    Activations Density 0.000%

    No Known Activations