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. 15-RESID-POST-AA
    6. 19493
    Prev
    Next
    INDEX
    Explanations

    TV show schedules

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     precip
    -0.09
    (password
    -0.09
    (prompt
    -0.08
    _peak
    -0.08
     વ્યક્ત
    -0.08
    obar
    -0.08
    Documento
    -0.08
    _fig
    -0.08
    (Query
    -0.08
    Pdf
    -0.08
    POSITIVE LOGITS
     sourced
    0.11
     imported
    0.11
     llegó
    0.09
     зарубеж
    0.09
     eure
    0.09
     وارد
    0.09
     लोकप्रिय
    0.09
     alten
    0.09
    Imported
    0.09
     arrivals
    0.09
    Activations Density 0.010%

    No Known Activations