© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 6403
    Prev
    Next
    INDEX
    Explanations

    academic references

    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
    imus
    -0.08
    intang
    -0.08
    íma
    -0.08
    -0.08
    -à
    -0.08
    acterial
    -0.08
    avit
    -0.08
    Txt
    -0.07
    imum
    -0.07
    imut
    -0.07
    POSITIVE LOGITS
     Este
    0.11
     Dos
    0.10
    Este
    0.09
    Dos
    0.09
    luiten
    0.09
     Dong
    0.09
     Dai
    0.08
     kriz
    0.08
     ganin
    0.08
     Recht
    0.08
    Activations Density 0.002%
    No Known Activations