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. 67837
    Prev
    Next
    INDEX
    Explanations

    ability

    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
     בעת
    -0.08
     dell
    -0.08
    Veh
    -0.07
    ในการ
    -0.07
     simple
    -0.07
     aa
    -0.07
    _del
    -0.07
     ven
    -0.07
     USING
    -0.07
     dem
    -0.07
    POSITIVE LOGITS
    "And
    0.08
    ić
    0.08
    _putchar
    0.08
     아
    0.08
     Panamá
    0.08
     proclam
    0.08
     Places
    0.07
     petitions
    0.07
     pilihan
    0.07
     근
    0.07
    Activations Density 0.002%

    No Known Activations