© 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. 6707
    Prev
    Next
    INDEX
    Explanations

    nu

    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
     Victor
    -0.08
    З
    -0.07
    ENER
    -0.07
    ERGY
    -0.07
     efficient
    -0.07
    Victor
    -0.07
    ANC
    -0.07
     NEC
    -0.07
     SAC
    -0.07
     equivalent
    -0.07
    POSITIVE LOGITS
    ola
    0.11
    omone
    0.09
    olat
    0.09
    os
    0.09
    osm
    0.09
    ostí
    0.09
    oding
    0.09
     hilar
    0.09
    omos
    0.09
    taf
    0.08
    Activations Density 0.000%

    No Known Activations