© 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. 50816
    Prev
    Next
    INDEX
    Explanations

    ti

    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
    �信
    -0.08
     चुकी
    -0.08
     Avis
    -0.08
    aum
    -0.08
    ेशन
    -0.08
    отно
    -0.07
    ुद
    -0.07
     ऑफिस
    -0.07
     Bask
    -0.07
     получили
    -0.07
    POSITIVE LOGITS
    Hand
    0.10
    hand
    0.09
    手
    0.09
    ன்ம
    0.08
    �
    0.08
    terms
    0.08
    Ę
    0.08
    STR
    0.08
     hand
    0.08
    EG
    0.07
    Activations Density 0.000%

    No Known Activations