© 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. 18765
    Prev
    Next
    INDEX
    Explanations

    HTML code

    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
    вается
    -0.09
    باشد
    -0.08
     anpil
    -0.08
     เช่น
    -0.08
    klär
    -0.08
     genauer
    -0.08
     дошта
    -0.08
    rscheinlichkeit
    -0.08
     ومح
    -0.08
     բառ
    -0.08
    POSITIVE LOGITS
    ाऊ
    0.08
    'adore
    0.08
    erse
    0.07
     Eindhoven
    0.07
    atit
    0.07
    rocess
    0.07
    _slide
    0.07
    न्न
    0.07
    _method
    0.07
    ometry
    0.07
    Activations Density 0.000%

    No Known Activations