© 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. 29682
    Prev
    Next
    INDEX
    Explanations

    iline

    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
    ണക്ക
    -0.08
    ാഴ്ച
    -0.08
     gait
    -0.07
    打
    -0.07
     indication
    -0.07
    时候
    -0.07
    性
    -0.07
    np
    -0.07
     Dashboard
    -0.07
    建议
    -0.07
    POSITIVE LOGITS
    IUnknown
    0.09
    alya
    0.08
     반드시
    0.08
    ipients
    0.08
    ipmap
    0.08
     stressing
    0.08
    ைத்து
    0.08
    .writer
    0.08
    uintptr
    0.08
    imitives
    0.07
    Activations Density 0.001%

    No Known Activations