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. 109003
    Prev
    Next
    INDEX
    Explanations

    diagon

    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
     IFR
    -0.09
     ironically
    -0.07
    -related
    -0.07
    actér
    -0.07
     مرتبط
    -0.07
     intimately
    -0.07
    ে
    -0.07
    zell
    -0.07
     lumin
    -0.07
     Ir
    -0.07
    POSITIVE LOGITS
    чу
    0.09
     Clarkson
    0.09
    ಗ್ರ
    0.08
     thick
    0.08
     ngati
    0.08
     Thick
    0.08
     hatta
    0.08
    няет
    0.08
     organização
    0.08
     egwu
    0.08
    Activations Density 0.006%

    No Known Activations