© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 23-RESID-POST-AA
    11. 49923
    Prev
    Next
    INDEX
    Explanations

    WS

    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
    观点
    -0.09
    ्दा
    -0.07
    breng
    -0.07
    .twitter
    -0.07
     narrated
    -0.07
    ontwikk
    -0.07
     extinct
    -0.07
     gelatin
    -0.07
    нять
    -0.07
    Newswire
    -0.07
    POSITIVE LOGITS
    Man
    0.09
    _CHILD
    0.09
    -Man
    0.09
    -Star
    0.08
    adow
    0.08
    _VISIBLE
    0.08
     minimal
    0.07
     stá
    0.07
     soma
    0.07
    0.07
    Activations Density 0.001%
    No Known Activations