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. 53292
    Prev
    Next
    INDEX
    Explanations

    general text

    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
    ikken
    -0.08
    120
    -0.08
     Cho
    -0.07
    tracted
    -0.07
     પ્રયાસ
    -0.07
     Скачать
    -0.07
    air
    -0.07
    .spring
    -0.07
     prochain
    -0.07
    273
    -0.07
    POSITIVE LOGITS
     puisse
    0.08
    �
    0.08
     vowels
    0.08
    组成
    0.08
    utora
    0.08
     famosos
    0.07
    ږي
    0.07
    АТО
    0.07
    条例
    0.07
    -famous
    0.07
    Activations Density 0.000%

    No Known Activations