© 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. 19-RESID-POST-AA
    11. 102695
    Prev
    Next
    INDEX
    Explanations

    keyboard

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     filtration
    -0.10
     incorporar
    -0.09
    年度
    -0.09
     renew
    -0.09
     inclusión
    -0.09
     incorporación
    -0.09
    omitempty
    -0.09
     triglycer
    -0.09
    อภิปราย
    -0.08
     annex
    -0.08
    POSITIVE LOGITS
     keyboard
    0.16
     teclado
    0.14
     клав
    0.14
     Keyboard
    0.13
    Keyboard
    0.13
     messed
    0.12
     shifted
    0.12
     swapped
    0.12
     clavier
    0.12
    _keyboard
    0.12
    Activations Density 0.004%

    No Known Activations