© 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. 18827
    Prev
    Next
    INDEX
    Explanations

    above

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     what
    -0.08
    җ
    -0.08
    what
    -0.08
     quei
    -0.08
     فإنه
    -0.07
     inderdaad
    -0.07
     izay
    -0.07
     அந்த
    -0.07
     deshalb
    -0.07
     aquel
    -0.07
    POSITIVE LOGITS
     above
    0.44
     acima
    0.39
    above
    0.36
     Above
    0.35
    Above
    0.35
     hierboven
    0.34
     выше
    0.34
     ABOVE
    0.30
     oben
    0.29
     bovenstaande
    0.29
    Activations Density 0.021%

    No Known Activations