© 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. 7-RESID-POST-AA
    11. 1344
    Prev
    Next
    INDEX
    Explanations

    drank

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rodents
    -0.10
     françaises
    -0.08
     rod
    -0.08
    uls
    -0.08
     rods
    -0.08
     verm
    -0.08
    ³
    -0.08
     franceses
    -0.08
    rome
    -0.08
     Midden
    -0.07
    POSITIVE LOGITS
    fast
    0.08
    feng
    0.08
    resents
    0.08
    advanced
    0.08
    _fast
    0.08
    迟
    0.07
    ainers
    0.07
     దీన
    0.07
    nar
    0.07
    ainer
    0.07
    Activations Density 0.403%

    No Known Activations