© 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. 608
    Prev
    Next
    INDEX
    Explanations

    translation

    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
     eldest
    -0.09
    thead
    -0.08
     datang
    -0.07
     Panasonic
    -0.07
     telesc
    -0.07
     monopol
    -0.07
    meno
    -0.07
    Monad
    -0.07
    Cable
    -0.07
     Monad
    -0.07
    POSITIVE LOGITS
    คำ
    0.10
     traduit
    0.10
     spelling
    0.10
     tradu
    0.09
     pronunciation
    0.09
     urlencode
    0.09
     અનુ
    0.09
     frase
    0.09
     QString
    0.09
     conveying
    0.09
    Activations Density 0.030%

    No Known Activations