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

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 78191
    Prev
    Next
    INDEX
    Explanations

    supernatural abilities

    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
    撑
    -0.08
    ិយ
    -0.08
    (height
    -0.08
     ukum
    -0.08
     Ross
    -0.08
     barrier
    -0.07
     boundary
    -0.07
    ​យ
    -0.07
     או
    -0.07
    'aj
    -0.07
    POSITIVE LOGITS
     reveal
    0.09
     revealing
    0.09
     Reve
    0.08
     revealed
    0.08
     Essence
    0.08
     essence
    0.08
    zitter
    0.08
    Reveal
    0.08
     deceit
    0.08
     olevan
    0.08
    Activations Density 0.010%

    No Known Activations