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. 46809
    Prev
    Next
    INDEX
    Explanations

    quotations

    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
     Beer
    -0.09
     bě
    -0.08
     beer
    -0.07
     pub
    -0.07
     cents
    -0.07
    olog
    -0.07
    াইজ
    -0.07
    amik
    -0.07
     IEEE
    -0.07
    sou
    -0.07
    POSITIVE LOGITS
    -reaching
    0.09
    itional
    0.08
     overlooking
    0.08
    غات
    0.08
    ressive
    0.08
    ว์
    0.08
     specifying
    0.08
    ضير
    0.08
    ynomials
    0.08
     منتجات
    0.08
    Activations Density 0.000%

    No Known Activations