© 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. 19-RESID-POST-AA
    11. 21530
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    939
    -0.08
    863
    -0.07
    ��
    -0.07
     оттен
    -0.07
    /ws
    -0.07
    785
    -0.07
    anticipated
    -0.07
    ેન્ડ
    -0.07
    igst
    -0.07
    íssimo
    -0.07
    POSITIVE LOGITS
     of
    0.09
     ही
    0.08
     हा
    0.08
    വി
    0.08
     होना
    0.08
     Beitrag
    0.08
     >>=
    0.08
     किन
    0.07
     पूर्ण
    0.07
     Masc
    0.07
    Activations Density 0.008%

    No Known Activations