© 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. 23-RESID-POST-AA
    11. 96398
    Prev
    Next
    INDEX
    Explanations

    double

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pital
    -0.08
    iveness
    -0.08
    hehe
    -0.08
    город
    -0.07
     id
    -0.07
     Rent
    -0.07
    嫁
    -0.07
     Bluff
    -0.07
    φων
    -0.07
     Rend
    -0.07
    POSITIVE LOGITS
     threat
    0.10
     Threat
    0.10
    header
    0.09
     teamwork
    0.09
     twintig
    0.09
     threatened
    0.09
     paquete
    0.08
    -header
    0.08
     threaten
    0.08
     threats
    0.08
    Activations Density 0.004%

    No Known Activations