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. 52953
    Prev
    Next
    INDEX
    Explanations

    industry

    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
     आल
    -0.08
     prue
    -0.08
     Ш
    -0.08
     चिं
    -0.08
     Almeida
    -0.08
     алын
    -0.08
     tranz
    -0.08
     sate
    -0.07
    {-
    -0.07
     empleados
    -0.07
    POSITIVE LOGITS
     burgeoning
    0.12
     diversification
    0.10
    发展
    0.09
     diversified
    0.09
     lucrative
    0.09
     områder
    0.09
     ontwikkeling
    0.09
    的发展
    0.09
     fördern
    0.08
     ambitions
    0.08
    Activations Density 0.022%

    No Known Activations