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. 27431
    Prev
    Next
    INDEX
    Explanations

    Sampling methods

    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
     تصميم
    -0.09
     MSS
    -0.08
     chassis
    -0.08
     экземпля
    -0.08
     YMCA
    -0.07
     Faux
    -0.07
    	RE
    -0.07
     SWOT
    -0.07
     JSP
    -0.07
    甲
    -0.07
    POSITIVE LOGITS
     trunc
    0.12
     pruning
    0.11
     percentile
    0.11
    truncate
    0.11
     truncate
    0.11
     cutoff
    0.10
     prune
    0.10
     gating
    0.10
    _threshold
    0.10
     filtering
    0.10
    Activations Density 0.002%

    No Known Activations