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. 48755
    Prev
    Next
    INDEX
    Explanations

    conjunctions and punctuation

    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
    (beta
    -0.09
     வளர
    -0.09
    ஒ
    -0.08
     capitalism
    -0.08
     மத
    -0.08
     வ
    -0.07
     entrants
    -0.07
     இணைய
    -0.07
    [w
    -0.07
    (valor
    -0.07
    POSITIVE LOGITS
     cartilage
    0.10
     cortex
    0.10
     поверхности
    0.09
     области
    0.09
     circumference
    0.09
     Bereich
    0.09
     positions
    0.09
     Bereiche
    0.09
     daño
    0.08
     cheeks
    0.08
    Activations Density 0.085%

    No Known Activations