© 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. 78048
    Prev
    Next
    INDEX
    Explanations

    <|end|>

    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
     sead
    -0.08
     wildfire
    -0.07
     мит
    -0.07
    .nick
    -0.07
     herum
    -0.07
     roadmap
    -0.07
     seizure
    -0.07
     dersom
    -0.07
     interesser
    -0.07
     verdient
    -0.07
    POSITIVE LOGITS
    條
    0.08
    �
    0.07
     QList
    0.07
    (to
    0.07
    خواه
    0.07
    (Output
    0.07
     வாழ
    0.07
    Wa
    0.07
    と
    0.07
     Ble
    0.07
    Activations Density 0.001%

    No Known Activations