© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 51204
    Prev
    Next
    INDEX
    Explanations

    inc

    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
    andescent
    -0.08
    flater
    -0.08
    ellation
    -0.08
    inct
    -0.08
     rigid
    -0.08
    'al
    -0.07
    ceiver
    -0.07
    ড়ে
    -0.07
    çados
    -0.07
    çado
    -0.07
    POSITIVE LOGITS
    idiendo
    0.12
    idir
    0.12
    isiones
    0.11
    isión
    0.10
    idenza
    0.10
    identes
    0.08
    URRENC
    0.08
    isas
    0.08
    ertid
    0.08
     sais
    0.07
    Activations Density 0.001%

    No Known Activations