© 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. 23-RESID-POST-AA
    11. 48039
    Prev
    Next
    INDEX
    Explanations

    desire, requirement

    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
     are
    -0.08
     sono
    -0.08
     availability
    -0.07
     pels
    -0.07
     possibilities
    -0.07
     capabilities
    -0.07
     са
    -0.07
     sont
    -0.07
     बातें
    -0.07
     magari
    -0.07
    POSITIVE LOGITS
     seeking
    0.22
     wanting
    0.20
     lacking
    0.20
     wishing
    0.20
     needing
    0.20
     undergoing
    0.19
     experiencing
    0.18
     prone
    0.18
     struggling
    0.17
     encountering
    0.17
    Activations Density 0.143%

    No Known Activations