© 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. 5676
    Prev
    Next
    INDEX
    Explanations

    form

    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
     обращения
    -0.08
    .equals
    -0.07
    ាន់
    -0.07
     katere
    -0.07
     مراج
    -0.07
    .chomp
    -0.06
    _FW
    -0.06
    ្នំពេញ
    -0.06
    ីឡ
    -0.06
    onso
    -0.06
    POSITIVE LOGITS
     forming
    0.49
     forms
    0.43
     formando
    0.43
     forman
    0.42
    形成
    0.41
     formar
    0.41
    forming
    0.41
     form
    0.38
     vormen
    0.37
     vormt
    0.36
    Activations Density 0.520%

    No Known Activations