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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112969
    Prev
    Next
    INDEX
    Explanations

    leap

    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
    aví
    -0.09
    あなた
    -0.07
    產品
    -0.07
    -alone
    -0.07
    DIY
    -0.07
     vague
    -0.07
     budete
    -0.07
    Laravel
    -0.07
    oltre
    -0.07
    제품
    -0.07
    POSITIVE LOGITS
     gereg
    0.09
    еи
    0.09
     wā
    0.09
     erkannt
    0.08
     马
    0.08
     favorable
    0.08
     handelt
    0.08
    adds
    0.07
     wetten
    0.07
     accommodated
    0.07
    Activations Density 0.002%

    No Known Activations