© 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. 48878
    Prev
    Next
    INDEX
    Explanations

    say "ief" ending

    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
    .usermodel
    -0.08
    ELL
    -0.08
     дости
    -0.08
     годов
    -0.08
     achievement
    -0.07
     adventure
    -0.07
     дал
    -0.07
    .hex
    -0.07
     distinguished
    -0.07
     привед
    -0.07
    POSITIVE LOGITS
    (de
    0.12
    /de
    0.11
    liction
    0.11
    .De
    0.11
    	de
    0.10
    .de
    0.10
    recated
    0.10
    ,de
    0.09
    (DE
    0.09
    érité
    0.09
    Activations Density 0.050%

    No Known Activations