© 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. 94545
    Prev
    Next
    INDEX
    Explanations

    Oort

    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
     campaigning
    -0.08
     www
    -0.08
     lic
    -0.08
    ಣ್ಣ
    -0.08
     vul
    -0.08
     audiovis
    -0.08
    дель
    -0.07
     film
    -0.07
     asphalt
    -0.07
     vegetation
    -0.07
    POSITIVE LOGITS
     Receive
    0.09
    ’extérieur
    0.09
     Schon
    0.09
    'extérieur
    0.09
     ontvangen
    0.09
    Receive
    0.09
    爷
    0.08
    _receive
    0.08
     Outside
    0.08
    .outer
    0.08
    Activations Density 0.002%

    No Known Activations