© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 47727
    Prev
    Next
    INDEX
    Explanations

    cognitive function

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     зин
    -0.09
    �
    -0.08
     Asked
    -0.08
    -0.08
     leftover
    -0.08
    	left
    -0.08
     Positioned
    -0.08
    	active
    -0.08
     сябе
    -0.08
     flagged
    -0.07
    POSITIVE LOGITS
     executive
    0.16
     decision
    0.16
     memory
    0.15
     cognition
    0.15
     concentration
    0.14
    Executive
    0.14
     નિર્ણય
    0.14
    Decision
    0.14
     attention
    0.14
     learning
    0.13
    Activations Density 0.044%
    No Known Activations