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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 12967
    Prev
    Next
    INDEX
    Explanations

    Life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kho
    -0.08
     nada
    -0.08
     matrícula
    -0.08
     रास्त
    -0.08
     frase
    -0.07
     optimisation
    -0.07
    途
    -0.07
     উপ
    -0.07
     acknowledge
    -0.07
     ausdr
    -0.07
    POSITIVE LOGITS
     sick
    0.09
    ubby
    0.08
     سیمه
    0.08
     waterproof
    0.08
    oplay
    0.07
    fance
    0.07
     弘
    0.07
     cmb
    0.07
     Sick
    0.07
     Been
    0.07
    Activations Density 0.001%

    No Known Activations