© 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. 47551
    Prev
    Next
    INDEX
    Explanations

    Dec

    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
     şə
    -0.07
    rial
    -0.07
     TAL
    -0.07
    creating
    -0.07
    ICENSE
    -0.07
     fehlt
    -0.07
     tala
    -0.07
    scriptions
    -0.07
    -0.07
     spherical
    -0.07
    POSITIVE LOGITS
    ided
    0.12
     décidé
    0.12
    [id
    0.11
     décider
    0.10
     decidió
    0.10
    idde
    0.10
    {id
    0.10
    	id
    0.10
     decidido
    0.09
    (id
    0.09
    Activations Density 0.001%
    No Known Activations