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. 43094
    Prev
    Next
    INDEX
    Explanations

    irrigation

    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
    バッグ
    -0.08
    ophen
    -0.08
     twenties
    -0.08
     stereotypes
    -0.08
    惯
    -0.08
    OID
    -0.08
     tulee
    -0.08
    ೇಷ
    -0.08
     GRAPH
    -0.07
    Media
    -0.07
    POSITIVE LOGITS
     व्यवस्था
    0.10
     ব্যবস্থা
    0.10
     системы
    0.09
     irrigation
    0.09
     sewer
    0.09
     ವ್ಯವಸ್ಥ
    0.09
    渠
    0.09
     medieval
    0.09
     сель
    0.08
     elaborate
    0.08
    Activations Density 0.009%

    No Known Activations