© 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. 11-RESID-POST-AA
    11. 490
    Prev
    Next
    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Scanner
    -0.07
    Movement
    -0.07
     troubled
    -0.07
     doch
    -0.07
    .slf
    -0.07
    fn
    -0.07
     Alf
    -0.07
    dul
    -0.07
     платеж
    -0.07
     Scriptures
    -0.07
    POSITIVE LOGITS
    aking
    0.08
     asing
    0.08
    లి
    0.08
    estes
    0.08
    ancis
    0.07
     conclus
    0.07
     juny
    0.07
     estes
    0.07
     Maio
    0.07
    יפ
    0.07
    Activations Density 0.137%

    No Known Activations