© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54554
    Prev
    Next
    INDEX
    Explanations

    helpful/supportive information

    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
     théâtre
    -0.08
     ADV
    -0.08
     justamente
    -0.08
     véritable
    -0.08
    _ADV
    -0.08
     Bam
    -0.07
    ADV
    -0.07
     pror
    -0.07
     mace
    -0.07
     effectivement
    -0.07
    POSITIVE LOGITS
     playful
    0.10
     fi
    0.08
    deny
    0.08
     joyful
    0.08
    .li
    0.08
     kiy
    0.07
    रीन
    0.07
    ள
    0.07
    ன்ற
    0.07
    ுந்த
    0.07
    Activations Density 0.552%

    No Known Activations