© 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. 29025
    Prev
    Next
    INDEX
    Explanations

    homology

    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
     дисцип
    -0.08
     sortes
    -0.08
     confines
    -0.08
    څ
    -0.08
    ிஷ
    -0.07
     agreg
    -0.07
    	props
    -0.07
     burocr
    -0.07
    _CONTROL
    -0.07
     aproxim
    -0.07
    POSITIVE LOGITS
    avuta
    0.09
    efe
    0.08
    oka
    0.08
    earned
    0.08
    -ab
    0.08
    /shared
    0.08
    arily
    0.07
    =find
    0.07
    endus
    0.07
    itive
    0.07
    Activations Density 0.002%

    No Known Activations