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. 12633
    Prev
    Next
    INDEX
    Explanations

    ArcPy scripts

    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
     stroke
    -0.09
     mio
    -0.09
    serde
    -0.08
    stroke
    -0.08
     holog
    -0.08
     integr
    -0.08
     Gol
    -0.08
     تور
    -0.08
    098
    -0.07
     :-)↵↵
    -0.07
    POSITIVE LOGITS
     héro
    0.09
     QFile
    0.08
    ровод
    0.08
     geren
    0.08
     Eligibility
    0.08
    (rename
    0.08
    岭
    0.08
    ックス
    0.07
    xtype
    0.07
    рип
    0.07
    Activations Density 0.004%

    No Known Activations