© 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. 11-RESID-POST-AA
    11. 54471
    Prev
    Next
    INDEX
    Explanations

    gener

    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
     stad
    -0.09
     alumin
    -0.09
     incurred
    -0.08
     Pey
    -0.08
     shipped
    -0.08
     HEL
    -0.08
     nette
    -0.08
     adaml
    -0.08
     drilled
    -0.08
     Fabian
    -0.08
    POSITIVE LOGITS
    .generate
    0.09
     cannabis
    0.08
     темат
    0.08
     storytelling
    0.08
     Garage
    0.07
     встав
    0.07
    Insert
    0.07
    Suggestions
    0.07
     Faux
    0.07
    _random
    0.07
    Activations Density 0.010%

    No Known Activations