© 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. 47535
    Prev
    Next
    INDEX
    Explanations

    amb/samb

    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
    leigh
    -0.08
    jų
    -0.08
    yddol
    -0.08
    ijnt
    -0.08
     juurde
    -0.08
    .optimizer
    -0.08
     zählen
    -0.08
     -------
    -0.08
     Bridal
    -0.08
     souff
    -0.08
    POSITIVE LOGITS
    ளம்
    0.08
     SC
    0.08
    Türkiye
    0.07
    *(
    0.07
    Vir
    0.07
    hang
    0.07
    alp
    0.07
    Sc
    0.07
    hun
    0.07
    Adaptive
    0.07
    Activations Density 0.002%

    No Known Activations