© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 196
    Prev
    Next
    INDEX
    Explanations

    surrounding

    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
     gad
    -0.09
    esz
    -0.09
    iversity
    -0.08
    Belle
    -0.08
    obile
    -0.08
    Gall
    -0.07
    estar
    -0.07
    including
    -0.07
     imkan
    -0.07
    qda
    -0.07
    POSITIVE LOGITS
     چو
    0.09
     каждого
    0.08
     accompany
    0.08
    _DM
    0.07
    /par
    0.07
     accompanies
    0.07
    aul
    0.07
    トップ
    0.07
     ingestion
    0.07
     каждой
    0.07
    Activations Density 0.040%

    No Known Activations