© 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. 31103
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    -tools
    -0.08
    .tools
    -0.08
    责
    -0.08
     dental
    -0.08
     MARK
    -0.07
     tools
    -0.07
     wills
    -0.07
    -local
    -0.07
    tools
    -0.07
    whose
    -0.07
    POSITIVE LOGITS
     triples
    0.09
     seller
    0.09
     insider
    0.08
     tuples
    0.08
     stranger
    0.08
     шанс
    0.08
     suggestion
    0.08
     yksi
    0.08
     workaround
    0.08
     товара
    0.08
    Activations Density 0.002%

    No Known Activations