© 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. 22385
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    addition
    -0.10
    implementation
    -0.10
    failure
    -0.09
    	number
    -0.09
    _parser
    -0.09
    measurement
    -0.09
    potential
    -0.09
    numero
    -0.09
    promotion
    -0.09
    definition
    -0.09
    POSITIVE LOGITS
    ▼
    0.14
    &nbsp
    0.14
    ▲
    0.14
    �
    0.13
    ✓
    0.13
     ▶
    0.13
    �
    0.13
    &amp
    0.13
    <span
    0.12
    ▶
    0.12
    Activations Density 0.015%

    No Known Activations