© 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. 11-RESID-POST-AA
    11. 134
    Prev
    Next
    INDEX
    Explanations

    range

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ちゃん
    -0.09
     pagina
    -0.08
    .mix
    -0.08
    iral
    -0.07
    स्त
    -0.07
     सुविधा
    -0.07
     sprawling
    -0.07
    ثير
    -0.07
    hrs
    -0.07
     comunica
    -0.07
    POSITIVE LOGITS
     sinu
    0.08
    怎样
    0.08
    دد
    0.08
     للحصول
    0.07
     دست
    0.07
    得到
    0.07
    趋
    0.07
    nå
    0.07
     valid
    0.07
     unsett
    0.07
    Activations Density 0.021%

    No Known Activations