© 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. 3-RESID-POST-AA
    11. 12953
    Prev
    Next
    INDEX
    Explanations

    ط

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    город
    -0.08
     彩
    -0.08
     skim
    -0.08
    imbi
    -0.08
    ILO
    -0.07
     clips
    -0.07
     sexuelles
    -0.07
     keinen
    -0.07
     жить
    -0.07
     selecting
    -0.07
    POSITIVE LOGITS
     avail
    0.10
     itil
    0.08
     aar
    0.07
     lector
    0.07
    ios
    0.07
     tavalla
    0.07
     utilis
    0.07
     optimum
    0.07
    พร้อม
    0.07
    optimal
    0.07
    Activations Density 0.000%

    No Known Activations