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. 109888
    Prev
    Next
    INDEX
    Explanations

    OS

    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
     હાજ
    -0.08
     driver's
    -0.08
     peace
    -0.08
     acr
    -0.08
    :value
    -0.08
     movilidad
    -0.08
     paz
    -0.08
    ست
    -0.07
     mobiele
    -0.07
     legalized
    -0.07
    POSITIVE LOGITS
     Essentially
    0.08
     Choose
    0.08
     informations
    0.08
     You
    0.08
     Indie
    0.08
     indie
    0.08
     Intermediate
    0.08
    ೆಯ
    0.08
    😭
    0.07
    orris
    0.07
    Activations Density 0.000%

    No Known Activations