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. 119213
    Prev
    Next
    INDEX
    Explanations

    2

    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
     நீங்கள்
    -0.08
     uni
    -0.07
     Han
    -0.07
    egang
    -0.07
     damos
    -0.07
     anao
    -0.07
     kaikki
    -0.07
     Sally
    -0.07
    holds
    -0.07
     uning
    -0.07
    POSITIVE LOGITS
    /(
    0.08
     constexpr
    0.08
    linewidth
    0.08
     dettagli
    0.08
     rai
    0.07
     Acht
    0.07
     konst
    0.07
    March
    0.07
    _PRINT
    0.07
     linewidth
    0.07
    Activations Density 0.181%

    No Known Activations