© 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. 21495
    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
     cientos
    -0.09
     whopping
    -0.09
    umlah
    -0.09
    _BIT
    -0.09
    ül
    -0.08
    数
    -0.08
    ологиялық
    -0.08
    umā
    -0.08
    ÉS
    -0.08
    ölt
    -0.08
    POSITIVE LOGITS
     pron
    0.11
     terminology
    0.09
    >'.↵
    0.09
     etc
    0.09
     emot
    0.08
     അവർ
    0.08
     punctuation
    0.08
     taxonomy
    0.08
     verbs
    0.08
     themselves
    0.08
    Activations Density 0.000%

    No Known Activations