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. 102915
    Prev
    Next
    INDEX
    Explanations

    can

    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
     줄
    -0.08
    力量
    -0.08
    offers
    -0.08
     ambientes
    -0.08
     động
    -0.08
    નો
    -0.07
     پڑھ
    -0.07
     ماحول
    -0.07
     mob
    -0.07
     Offers
    -0.07
    POSITIVE LOGITS
     rinc
    0.09
     analyze
    0.08
     specifics
    0.08
     দেখি
    0.08
     treat
    0.08
     revisit
    0.08
     specify
    0.08
     conceive
    0.08
     назвать
    0.08
     foresee
    0.07
    Activations Density 0.096%

    No Known Activations