© 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. 3-RESID-POST-AA
    11. 2884
    Prev
    Next
    INDEX
    Explanations

    085

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     synd
    -0.08
     alc
    -0.07
    orni
    -0.07
     sext
    -0.07
     Synd
    -0.07
    -0.07
    timeline
    -0.07
     gan
    -0.07
    ALG
    -0.07
     bestens
    -0.07
    POSITIVE LOGITS
     Legends
    0.08
     Jackie
    0.08
     vak
    0.07
     Danger
    0.07
     Shannon
    0.07
    .dom
    0.07
    界
    0.07
    TP
    0.07
    (beta
    0.07
    તે
    0.07
    Activations Density 0.002%
    No Known Activations