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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19164
    Prev
    Next
    INDEX
    Explanations

    say numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     refleja
    -0.08
    彩金
    -0.08
     eligibility
    -0.07
    套
    -0.07
     Pū
    -0.07
     chargers
    -0.07
     выиг
    -0.07
     Reflect
    -0.07
    غيير
    -0.07
    Bonus
    -0.07
    POSITIVE LOGITS
     headphone
    0.10
     angene
    0.10
     quieter
    0.10
     शांत
    0.09
     louder
    0.09
     শান্ত
    0.09
    เสียง
    0.09
     workplace
    0.09
     calmer
    0.09
     harmless
    0.08
    Activations Density 0.002%

    No Known Activations