© 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. 65359
    Prev
    Next
    INDEX
    Explanations

    milk/pumping

    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
    -0.08
     datap
    -0.08
    077
    -0.07
     transaction
    -0.07
    .......
    -0.07
     sweeping
    -0.07
    점
    -0.07
     presenta
    -0.07
     paseo
    -0.07
    Republic
    -0.07
    POSITIVE LOGITS
     geist
    0.09
    -producing
    0.09
     മണിക്ക
    0.09
     produzido
    0.09
     produire
    0.08
     beschikbaar
    0.08
     productie
    0.08
     reservoirs
    0.08
    每天
    0.08
    -production
    0.08
    Activations Density 0.003%
    No Known Activations