© 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. 54693
    Prev
    Next
    INDEX
    Explanations

    m

    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
     Davenport
    -0.08
    Lite
    -0.08
     અમદાવાદ
    -0.08
     criticizing
    -0.08
     citing
    -0.08
     նրանք
    -0.08
     կարծում
    -0.07
    Wire
    -0.07
    ოვან
    -0.07
     ասում
    -0.07
    POSITIVE LOGITS
     stabil
    0.08
    onal
    0.08
    enarios
    0.07
     estrateg
    0.07
     generous
    0.07
     Mort
    0.07
    จะ
    0.07
    _descriptor
    0.07
     Cuando
    0.07
     estabil
    0.07
    Activations Density 0.000%

    No Known Activations