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. 112163
    Prev
    Next
    INDEX
    Explanations

    design

    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
     arro
    -0.09
     tidal
    -0.09
    bron
    -0.08
     verse
    -0.08
    tid
    -0.08
     وط
    -0.07
     Roche
    -0.07
     impeachment
    -0.07
     repe
    -0.07
    caller
    -0.07
    POSITIVE LOGITS
     aesthetics
    0.11
     aesthetic
    0.10
     эстет
    0.09
     sass
    0.09
     Canva
    0.09
     disciplines
    0.09
     professionals
    0.09
     aesthetically
    0.08
     profissionais
    0.08
     respons
    0.08
    Activations Density 0.042%

    No Known Activations