© 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. 6514
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    Parametros
    -0.09
     administração
    -0.08
    =torch
    -0.08
     elevar
    -0.08
    (Stage
    -0.08
     méth
    -0.08
    .JScroll
    -0.08
     kveld
    -0.08
     parâmetros
    -0.08
     activité
    -0.07
    POSITIVE LOGITS
    ress
    0.08
    resh
    0.07
    常
    0.07
    'ch
    0.07
    /down
    0.07
     favors
    0.07
     Antigua
    0.07
    res
    0.07
    ামের
    0.07
    వ
    0.07
    Activations Density 0.000%

    No Known Activations