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. 48957
    Prev
    Next
    INDEX
    Explanations

    ful

    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
    biz
    -0.09
    wife
    -0.08
     éta
    -0.08
    Above
    -0.08
     Above
    -0.08
     shielding
    -0.08
    -dessus
    -0.08
    above
    -0.07
    58
    -0.07
    was
    -0.07
    POSITIVE LOGITS
     легко
    0.08
     gedrag
    0.08
    走势
    0.08
     bient
    0.08
    ystal
    0.08
     скоро
    0.08
     outcome
    0.08
     omstandigheden
    0.08
     поведения
    0.08
     Cryptocurrency
    0.08
    Activations Density 0.005%

    No Known Activations