© 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 EvalsExportsAPI 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. 20195
    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
     hoʻol
    -0.12
     მისი
    -0.12
     bhíonn
    -0.11
    აბილ
    -0.11
     bhaint
    -0.11
     հնար
    -0.11
     bhaineann
    -0.11
     შეძლ
    -0.11
     hlok
    -0.11
     dhéanamh
    -0.11
    POSITIVE LOGITS
     ':'
    0.11
    -separated
    0.10
    (':
    0.10
    ity
    0.10
    colon
    0.10
    sen
    0.09
    delimiter
    0.09
     punctuation
    0.09
    (';
    0.09
     delimiter
    0.09
    Activations Density 0.000%

    No Known Activations