© 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. 31167
    Prev
    Next
    INDEX
    Explanations

    vegan bowls

    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
     obstruction
    -0.08
    stdafx
    -0.08
     తెల
    -0.08
    Abort
    -0.08
     nobles
    -0.08
     seized
    -0.07
     destiné
    -0.07
    ింట
    -0.07
     anticipation
    -0.07
     destinados
    -0.07
    POSITIVE LOGITS
     veggies
    0.10
     salmon
    0.09
     sunflower
    0.09
    reiche
    0.09
    emoji
    0.08
     hende
    0.08
     avocado
    0.08
     feta
    0.08
     greens
    0.08
     quinoa
    0.08
    Activations Density 0.017%

    No Known Activations