© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 75603
    Prev
    Next
    INDEX
    Explanations

    scientific experiments

    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
     باشد
    -0.08
    ائیں
    -0.08
    န်
    -0.08
     aan
    -0.08
     erfüllt
    -0.08
    irgí
    -0.08
     insured
    -0.08
    采取
    -0.08
    สถาน
    -0.08
     administrativos
    -0.08
    POSITIVE LOGITS
     cannabinoids
    0.08
    GBT
    0.08
     cannabino
    0.08
    HB
    0.07
    pathy
    0.07
     blah
    0.07
    Lang
    0.07
     Behavioral
    0.07
     mennes
    0.07
    创造
    0.07
    Activations Density 0.045%

    No Known Activations