Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 53289
    Prev
    Next
    INDEX
    Explanations

    Code snippets execution instructions

    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
    776
    -0.08
    στη
    -0.08
     Disorders
    -0.07
     disorders
    -0.07
    417
    -0.07
    urement
    -0.07
    ensity
    -0.07
    assen
    -0.07
     uite
    -0.07
     Mortal
    -0.07
    POSITIVE LOGITS
     Ë
    0.09
     Preisen
    0.08
     प्रस
    0.08
    زيادة
    0.08
    freiheit
    0.08
     colleg
    0.08
     programmation
    0.08
    adaa
    0.07
    _EVENT
    0.07
     clás
    0.07
    Activations Density 0.006%

    No Known Activations