© 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. 45428
    Prev
    Next
    INDEX
    Explanations

    filtering, cutting, shapes

    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
     phantom
    -0.09
    -ab
    -0.08
    _ab
    -0.07
     around
    -0.07
     concret
    -0.07
    య్య
    -0.07
     repeated
    -0.07
    Preset
    -0.07
    todo
    -0.07
    Primer
    -0.07
    POSITIVE LOGITS
     شم
    0.08
     связано
    0.08
     Cyr
    0.08
     manufacturing
    0.08
     estabelecer
    0.08
    ளை
    0.08
    فرادی
    0.08
    OBILE
    0.08
    жается
    0.07
    nete
    0.07
    Activations Density 0.000%

    No Known Activations