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. 88032
    Prev
    Next
    INDEX
    Explanations

    a

    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
     через
    -0.08
     використов
    -0.07
    (updated
    -0.07
    663
    -0.07
     poist
    -0.07
     formatted
    -0.07
     tarih
    -0.07
    (from
    -0.07
     доступ
    -0.07
     centered
    -0.07
    POSITIVE LOGITS
     aport
    0.09
    aben
    0.08
     Raster
    0.08
     Postal
    0.08
     Euchar
    0.08
     electrician
    0.08
     depl
    0.08
     Winston
    0.08
    BYTE
    0.08
    ığın
    0.07
    Activations Density 0.000%

    No Known Activations