© 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. 65336
    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
     mechanisms
    -0.09
     wearable
    -0.08
    ර
    -0.08
    都是
    -0.07
     recommande
    -0.07
     Capitol
    -0.07
     warme
    -0.07
     Kons
    -0.07
    机制
    -0.07
     embodied
    -0.07
    POSITIVE LOGITS
    yness
    0.08
     ومح
    0.08
     بمن
    0.08
    वी
    0.07
    game
    0.07
     א
    0.07
     איל
    0.07
     yil
    0.07
    Three
    0.07
     minors
    0.07
    Activations Density 0.009%

    No Known Activations