© 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. 20484
    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
     fekk
    -0.08
     lucro
    -0.08
     soll's
    -0.07
     gouf
    -0.07
    არო
    -0.07
     povas
    -0.07
    ’ant
    -0.07
     shacabka
    -0.07
    apia
    -0.07
     пәй
    -0.07
    POSITIVE LOGITS
    0.26
     двад
    0.20
     vingt
    0.17
     Forty
    0.16
     لعام
    0.16
     Twenty
    0.16
     दस
    0.15
     twenty
    0.14
     forty
    0.14
     Thirty
    0.14
    Activations Density 0.294%

    No Known Activations