© 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. 24563
    Prev
    Next
    INDEX
    Explanations

    non-English, Errors

    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
     clam
    -0.09
    MG
    -0.09
    female
    -0.09
    Destroyed
    -0.08
     tether
    -0.08
    Female
    -0.08
     Frost
    -0.07
    elow
    -0.07
    콩
    -0.07
     Blatt
    -0.07
    POSITIVE LOGITS
    /error
    0.10
     رخ
    0.10
     leh
    0.08
     log
    0.08
     error
    0.08
     judgment
    0.08
     erreur
    0.08
     errores
    0.08
    (error
    0.08
     outright
    0.07
    Activations Density 0.005%

    No Known Activations