© 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. 23-RESID-POST-AA
    11. 49365
    Prev
    Next
    INDEX
    Explanations

    ط

    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
     curso
    -0.09
     mountains
    -0.08
     noses
    -0.08
    课
    -0.08
     knives
    -0.07
    課
    -0.07
    курс
    -0.07
    -bold
    -0.07
    mooth
    -0.07
     cursos
    -0.07
    POSITIVE LOGITS
    بيع
    0.09
    ریح
    0.09
    راح
    0.08
    راحی
    0.08
    uyo
    0.08
    .ve
    0.08
    ורת
    0.08
     tapped
    0.08
    鸿
    0.07
    ination
    0.07
    Activations Density 0.000%

    No Known Activations