© 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. 96834
    Prev
    Next
    INDEX
    Explanations

    fashion brands

    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
     луч
    -0.09
     mejor
    -0.09
     hende
    -0.08
     хочу
    -0.08
     www
    -0.08
     meglio
    -0.08
     хочет
    -0.08
     panor
    -0.08
    魅
    -0.07
     أل
    -0.07
    POSITIVE LOGITS
    -gap
    0.09
    output
    0.08
    -Aus
    0.08
    Gap
    0.07
    FIELD
    0.07
     Gap
    0.07
    UPLOAD
    0.07
    ueira
    0.07
    -acde
    0.07
    -X
    0.07
    Activations Density 0.001%

    No Known Activations