© 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. 45304
    Prev
    Next
    INDEX
    Explanations

    Jason Mraz

    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
     monstrous
    -0.10
     kepala
    -0.08
     Occidental
    -0.08
     Ang
    -0.08
     teste
    -0.08
     Grund
    -0.08
     Norm
    -0.08
     escalating
    -0.08
     fierc
    -0.08
    Contours
    -0.07
    POSITIVE LOGITS
     warmth
    0.09
     unob
    0.08
     workouts
    0.08
     teamed
    0.08
     coordinated
    0.08
     concerts
    0.08
     upbeat
    0.08
    वे
    0.08
     pursuits
    0.08
     Yusuf
    0.08
    Activations Density 0.083%

    No Known Activations