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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48042
    Prev
    Next
    INDEX
    Explanations

    г

    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
    sx
    -0.07
    ijski
    -0.07
     gn
    -0.07
    051
    -0.07
    _LOCAL
    -0.07
    GAN
    -0.07
     ap
    -0.07
    TC
    -0.07
    AP
    -0.07
    apped
    -0.07
    POSITIVE LOGITS
    лины
    0.09
    нили
    0.09
    eline
    0.09
    рева
    0.08
    раста
    0.08
    овора
    0.08
    eday
    0.08
    нений
    0.08
    elines
    0.08
    ης
    0.08
    Activations Density 0.005%

    No Known Activations