© 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. 19-RESID-POST-AA
    11. 102995
    Prev
    Next
    INDEX
    Explanations

    text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "is
    -0.12
    .operator
    -0.10
    (operator
    -0.10
    	operator
    -0.10
    "in
    -0.09
    -being
    -0.09
    .environment
    -0.09
    -other
    -0.09
    (character
    -0.09
    .dictionary
    -0.09
    POSITIVE LOGITS
     given
    0.09
     ↵↵
    0.08
     depi
    0.08
     cyangwa
    0.08
     özellikle
    0.08
    和
    0.08
      ↵↵
    0.08
     […]↵↵
    0.08
    探
    0.07
    勿
    0.07
    Activations Density 0.006%

    No Known Activations