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. 74780
    Prev
    Next
    INDEX
    Explanations

    absent-minded, unfocused

    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
     positional
    -0.08
    phe
    -0.08
     ewu
    -0.08
     earth
    -0.08
     consideration
    -0.07
     churches
    -0.07
     dae
    -0.07
     bode
    -0.07
    Grouped
    -0.07
    .These
    -0.07
    POSITIVE LOGITS
     distracted
    0.10
     inatt
    0.10
     dold
    0.08
     numb
    0.08
     impaired
    0.08
     ralent
    0.08
     blanks
    0.08
    事故
    0.08
     hypnot
    0.08
     خاط
    0.08
    Activations Density 0.024%

    No Known Activations