© 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. 47688
    Prev
    Next
    INDEX
    Explanations

    эк

    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
     hyzmat
    -0.09
    łos
    -0.08
    ávy
    -0.08
     disruptive
    -0.08
     rö
    -0.08
     Rouge
    -0.08
    Servico
    -0.08
     হাজার
    -0.08
    ოშ
    -0.08
     हजार
    -0.07
    POSITIVE LOGITS
    в
    0.15
    В
    0.11
    vival
    0.11
    v
    0.10
     В
    0.09
    .u
    0.08
    ві
    0.08
    u
    0.08
    Ui
    0.08
    виз
    0.08
    Activations Density 0.001%

    No Known Activations