© 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. 95526
    Prev
    Next
    INDEX
    Explanations

    administrative

    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
    Ass
    -0.08
    Changes
    -0.08
    Adjust
    -0.08
    PLC
    -0.07
    Char
    -0.07
     hydro
    -0.07
    da
    -0.07
     изменений
    -0.07
     changes
    -0.07
     noodle
    -0.07
    POSITIVE LOGITS
     formul
    0.09
     Formular
    0.08
    ույթ
    0.08
    -doc
    0.08
    esent
    0.08
     formular
    0.08
     formulations
    0.08
     boutique
    0.08
     निर्द
    0.07
     Jubil
    0.07
    Activations Density 0.000%

    No Known Activations