© 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. 11-RESID-POST-AA
    11. 70875
    Prev
    Next
    INDEX
    Explanations

    meeting

    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
    phans
    -0.08
    abung
    -0.08
    ��
    -0.08
    arach
    -0.08
     sobretudo
    -0.08
    엄
    -0.08
     lancement
    -0.07
    haft
    -0.07
     EObject
    -0.07
    wissen
    -0.07
    POSITIVE LOGITS
     rivalry
    0.10
    双方
    0.09
    _between
    0.09
     تاریخ
    0.08
     gemeinsamen
    0.08
     gegense
    0.08
     historii
    0.08
     matchup
    0.08
     истории
    0.08
     گذشته
    0.08
    Activations Density 0.027%

    No Known Activations