© 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. 54684
    Prev
    Next
    INDEX
    Explanations

    best case

    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
     dian
    -0.07
    _ps
    -0.07
     printer
    -0.07
            ↵        ↵
    -0.07
     pirate
    -0.07
    xiv
    -0.07
                ↵            ↵
    -0.07
    Lots
    -0.07
    зор
    -0.07
    pon
    -0.07
    POSITIVE LOGITS
    _ALREADY
    0.08
     leichter
    0.08
     Recogn
    0.08
    ờ
    0.08
     scenarios
    0.07
     reconocer
    0.07
     suaves
    0.07
    .parallel
    0.07
    軽
    0.07
    allinen
    0.07
    Activations Density 0.001%

    No Known Activations