© 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. 79016
    Prev
    Next
    INDEX
    Explanations

    »

    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
     선언
    -0.08
     purge
    -0.08
     Sweepstakes
    -0.08
    pur
    -0.08
     purifier
    -0.07
     Pur
    -0.07
    Pur
    -0.07
    Semaphore
    -0.07
     boosters
    -0.07
     declara
    -0.07
    POSITIVE LOGITS
     folders
    0.08
    ../../
    0.08
     archivos
    0.08
     ../../
    0.08
    二
    0.08
    _files
    0.08
     files
    0.08
     hierarchy
    0.08
    0.08
    ritable
    0.07
    Activations Density 0.015%
    No Known Activations